© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3714
    Prev
    Next
    INDEX
    Explanations

    the word "user" and words associated with users

    oai_token-act-pair · gemini-2.0-flash

    user

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ...
    -0.51
    AxisAlignment
    -0.50
     he
    -0.50
    al
    -0.48
    ActiveRecord
    -0.47
     B
    -0.47
    _
    -0.45
    ap
    -0.44
    as
    -0.44
     Knapp
    -0.43
    POSITIVE LOGITS
     itſelf
    1.34
     myſelf
    1.31
     ainfi
    1.26
     Theſe
    1.20
     nahilalakip
    1.20
     pleaſure
    1.18
     uſe
    1.17
     Anſ
    1.16
     ſche
    1.15
     Eſ
    1.15
    Activations Density 0.183%

    No Known Activations