© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9621
    Prev
    Next
    INDEX
    Explanations

    conjunctions such as "and" along with prepositions such as "to" to denote relationships between ideas.

    oai_token-act-pair · gemini-2.0-flash

    concepts related to personal development

    np_token-act-pair-logits · gpt-4o-mini

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     travailleurs
    -0.50
     and
    -0.49
     spectateurs
    -0.49
    &__
    -0.48
     réfugiés
    -0.48
     fournisseurs
    -0.47
     écrans
    -0.46
     consommateurs
    -0.45
     pères
    -0.45
     ouvriers
    -0.45
    POSITIVE LOGITS
     inspirations
    0.95
     strengths
    0.88
     approaches
    0.87
     sentiments
    0.84
     behaviours
    0.84
     philosophies
    0.83
     practices
    0.83
     motivations
    0.83
     behaviors
    0.82
     tastes
    0.81
    Activations Density 3.240%

    No Known Activations