© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1374
    Prev
    Next
    INDEX
    Explanations

    language around ethical and legal consent, or fundraising and manipulation

    oai_token-act-pair · gemini-2.0-flash

    asking/requesting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Giving
    -0.65
    Giving
    -0.65
     giving
    -0.64
    给了
    -0.60
     Gave
    -0.58
     supplying
    -0.58
     gave
    -0.58
     give
    -0.58
    GIVE
    -0.57
     Paying
    -0.57
    POSITIVE LOGITS
     asking
    1.15
    asking
    1.02
     request
    1.01
    Asking
    0.99
     requesting
    0.96
     Asking
    0.96
    request
    0.94
     ask
    0.92
     Request
    0.91
     asks
    0.90
    Activations Density 1.533%

    No Known Activations