© 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. 9259
    Prev
    Next
    INDEX
    Explanations

    punctuation and words related to sports scores

    oai_token-act-pair · 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
    AddTagHelper
    -0.67
    LiveData
    -0.47
    ForResult
    -0.43
    tagext
    -0.42
    ellees
    -0.41
     rentrée
    -0.41
     INVENTION
    -0.41
    OpenHelper
    -0.41
    jstor
    -0.40
    calloc
    -0.40
    POSITIVE LOGITS
     Paglinawan
    0.90
    ρίζ
    0.68
     jeter
    0.64
    ]--;
    0.60
     Италијани
    0.57
    uride
    0.56
     ainfi
    0.56
     Roskov
    0.56
    ++];
    0.55
    atify
    0.55
    Activations Density 3.629%

    No Known Activations