© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3056
    Prev
    Next
    INDEX
    Explanations

    code syntax and related terms (e.g., brackets, parenthesis, double, int, result, etc.)

    oai_token-act-pair · gemini-2.0-flash

    code punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    addCriterion
    -0.83
    évaluateur
    -0.68
    Erreferentziak
    -0.67
    下载附件
    -0.66
    ագրություններ
    -0.66
     disponibilités
    -0.63
    MessageOf
    -0.63
    “
    -0.62
    ⓧ
    -0.61
     跳转至
    -0.59
    POSITIVE LOGITS
     pleaſure
    0.59
     ſtate
    0.57
     %%
    0.56
    GHIJKLM
    0.56
     #:
    0.55
     eſt
    0.54
     houſe
    0.54
     deſt
    0.53
     Monfieur
    0.52
     greateſt
    0.51
    Activations Density 11.911%

    No Known Activations