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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 852
    Prev
    Next
    INDEX
    Explanations

    SQL code

    oai_token-act-pair · gemini-2.0-flash

    Code/database context

    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
     Italijanski
    -0.92
    AsUp
    -0.84
    SharedCtor
    -0.81
     تضيفلها
    -0.77
    SharedDtor
    -0.76
    ValueStyle
    -0.75
    MigrationBuilder
    -0.73
    tvguidetime
    -0.71
    OGND
    -0.71
    TypedDataSet
    -0.68
    POSITIVE LOGITS
    zeera
    0.51
    δου
    0.47
    paddingVertical
    0.46
    Lauf
    0.43
     Lauf
    0.43
     bãi
    0.42
     مرجع
    0.41
     ctrl
    0.40
    entibus
    0.40
     hyd
    0.40
    Activations Density 13.795%

    No Known Activations