© 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. 12413
    Prev
    Next
    INDEX
    Explanations

    the word 'bench'

    oai_token-act-pair · gemini-2.0-flash

    bench

    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
    <bos>
    -0.78
    Filmografie
    -0.75
    ioutil
    -0.69
     ovvero
    -0.69
     disambiguazione
    -0.68
    InjectAttribute
    -0.67
    Filmography
    -0.64
    WebControls
    -0.63
    Šaltiniai
    -0.63
     Efq
    -0.63
    POSITIVE LOGITS
     Nore
    0.74
    __*/
    0.72
    AnchorStyles
    0.66
    })));
    0.66
    hate
    0.60
    </tbody>
    0.60
    ----</
    0.58
    icias
    0.58
     Ums
    0.58
    (';
    0.58
    Activations Density 0.467%

    No Known Activations