© 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. 12377
    Prev
    Next
    INDEX
    Explanations

    a combination of names and/or Italian words and numbers

    oai_token-act-pair · gemini-2.0-flash

    Code, names, and foreign language

    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
     those
    -0.77
     due
    -0.71
    due
    -0.63
    Due
    -0.57
     Due
    -0.57
    Those
    -0.52
    )$_
    -0.51
    those
    -0.51
     DUE
    -0.50
     Debido
    -0.49
    POSITIVE LOGITS
     Roskov
    0.88
    queryInterface
    0.78
    MigrationBuilder
    0.73
    enterOuterAlt
    0.69
     le
    0.66
     quelle
    0.65
    OGND
    0.64
    ParallelGroup
    0.62
    ConstraintMaker
    0.60
     externes
    0.59
    Activations Density 0.309%

    No Known Activations