© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 430
    Prev
    Next
    INDEX
    Explanations

    the prefix "un" and the character sequences "asc", "dec", "dc", "disc", inc", and "fc"

    oai_token-act-pair · gemini-2.0-flash

    disc

    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
    tvguidetime
    -0.77
     الرياضيه
    -0.68
    a
    -0.63
    ########.
    -0.60
    able
    -0.57
    o
    -0.56
    opp
    -0.56
    WithIOException
    -0.56
     InputDecoration
    -0.55
    aA
    -0.54
    POSITIVE LOGITS
     Tung
    0.44
    tabular
    0.43
    ViewImports
    0.43
    emballage
    0.43
    phany
    0.42
     CURIAM
    0.42
    ArgsConstructor
    0.42
    DoubleQuotes
    0.42
    хьтан
    0.41
     Tep
    0.41
    Activations Density 4.994%

    No Known Activations