© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6400
    Prev
    Next
    INDEX
    Explanations

    pronouns being used to refer to people

    oai_token-act-pair · gemini-2.0-flash

    dialogue

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     NSCoder
    -0.69
     Incompatible
    -0.59
     Forth
    -0.59
    InjectAttribute
    -0.58
    談社
    -0.58
    PANY
    -0.57
     contextLoads
    -0.57
     zvuky
    -0.56
     scoperto
    -0.56
    zzleHttp
    -0.55
    POSITIVE LOGITS
    Personendaten
    0.49
    WEBPACK
    0.47
     alibi
    0.46
    Билгалдахарш
    0.46
    StandardCharsets
    0.45
     referenties
    0.42
    fuels
    0.42
    เอก
    0.41
    maid
    0.41
    addChild
    0.41
    Activations Density 5.002%

    No Known Activations