© 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. 11610
    Prev
    Next
    INDEX
    Explanations

    the word "routine" and words associated with women

    oai_token-act-pair · gemini-2.0-flash

    routine

    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
     Monfieur
    -1.15
     purpoſe
    -1.11
     pleaſure
    -1.09
     ſche
    -1.09
     Reſ
    -1.03
     ſtand
    -1.02
     ſy
    -1.02
     ſtate
    -1.00
     cauſe
    -1.00
     Inſ
    -0.99
    POSITIVE LOGITS
     or
    0.65
     in
    0.65
     ma
    0.59
     of
    0.55
     acesta
    0.54
     just
    0.53
     (
    0.52
     has
    0.52
    --*/
    0.50
     I
    0.50
    Activations Density 0.665%

    No Known Activations