© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4798
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate source-code or technical documentation

    oai_token-act-pair · gemini-2.0-flash

    Code diffs

    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
    a
    -1.63
    e
    -1.46
    v
    -1.44
    i
    -1.40
    h
    -1.39
    u
    -1.37
    w
    -1.36
    as
    -1.35
    re
    -1.35
    in
    -1.35
    POSITIVE LOGITS
    ratulations
    1.16
    iffion
    1.09
    polation
    1.09
    iffance
    1.08
    othesis
    1.05
    hematical
    1.02
    bibfield
    1.00
    elfare
    1.00
    encils
    0.99
    fible
    0.98
    Activations Density 29.653%

    No Known Activations