© 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. 5029
    Prev
    Next
    INDEX
    Explanations

    words related to power and attacks in the context of a character or user

    oai_token-act-pair · gemini-2.0-flash

    attacks

    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
    Datuak
    -0.77
    󠁢
    -0.69
    feira
    -0.68
     Audiodateien
    -0.66
    Hentet
    -0.59
    igshid
    -0.58
     Souha
    -0.57
     الحره
    -0.57
    ResourceBundle
    -0.56
    tetlen
    -0.56
    POSITIVE LOGITS
     nakalista
    0.57
    RepeatedField
    0.52
     throwing
    0.46
    auw
    0.46
    throw
    0.46
     isSet
    0.46
     throw
    0.45
     throws
    0.44
    esModule
    0.44
    ArrowToggle
    0.44
    Activations Density 5.771%

    No Known Activations