© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6674
    Prev
    Next
    INDEX
    Explanations

    prepositions, possessives, and related connecting words

    oai_token-act-pair · gemini-2.0-flash

    many, numerous

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Ibid
    -0.53
     wiedzieć
    -0.45
    buie
    -0.45
    ôtel
    -0.43
    InlineData
    -0.43
     eventdata
    -0.42
     cherchés
    -0.42
    ientôt
    -0.41
    ரை
    -0.41
    erdings
    -0.41
    POSITIVE LOGITS
     many
    2.25
    many
    1.98
     MANY
    1.81
     numerous
    1.77
     multiple
    1.73
    Many
    1.71
     Many
    1.71
     several
    1.66
     muchos
    1.56
    Numerous
    1.55
    Activations Density 2.368%

    No Known Activations