© 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. 10940
    Prev
    Next
    INDEX
    Explanations

    hyphenated words, particularly technical terms, and often with "in-" as a prefix

    oai_token-act-pair · gemini-2.0-flash

    -

    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
     Theſe
    -0.87
     Monfieur
    -0.84
     Efq
    -0.84
     useHistory
    -0.83
    .}~\
    -0.81
     ainfi
    -0.81
     feroit
    -0.79
    ^(@)
    -0.77
    bibfield
    -0.77
     Theaters
    -0.77
    POSITIVE LOGITS
     the
    0.65
    Hentet
    0.59
    ↵
    0.57
    addGap
    0.57
     in
    0.51
    Autoritní
    0.50
     pre
    0.49
    ,
    0.48
    out
    0.48
     their
    0.47
    Activations Density 1.039%

    No Known Activations