© 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. 3629
    Prev
    Next
    INDEX
    Explanations

    instances of the word "stuff" and references to men and women

    oai_token-act-pair · gemini-2.0-flash

    men

    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
    ,
    -1.30
    .
    -1.05
     and
    -1.04
     to
    -1.02
     in
    -0.91
     (
    -0.76
     for
    -0.75
     on
    -0.71
     with
    -0.69
     will
    -0.68
    POSITIVE LOGITS
     Theſe
    1.52
     Monfieur
    1.13
     étoient
    1.13
     becauſe
    1.11
     Jefus
    1.10
     myſelf
    1.08
     himſelf
    1.07
     Beſ
    1.05
     avoient
    1.05
     auroit
    1.05
    Activations Density 3.623%

    No Known Activations