© 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. 7316
    Prev
    Next
    INDEX
    Explanations

    the phrase "all"

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "all"

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

    say "new" words

    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
     Bost
    -0.54
    Демографія
    -0.52
    érées
    -0.50
     "}";
    -0.49
    orians
    -0.49
    fuhr
    -0.46
    orius
    -0.45
     respectivement
    -0.45
    énier
    -0.44
     giapp
    -0.44
    POSITIVE LOGITS
    round
    0.75
    ]='\
    0.73
     round
    0.70
    ROUND
    0.68
    Round
    0.65
     dotenv
    0.62
     ROUND
    0.59
    around
    0.59
    principalColumn
    0.59
     encomp
    0.58
    Activations Density 0.221%

    No Known Activations