© 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. 14849
    Prev
    Next
    INDEX
    Explanations

    a mix of code snippets, foreign languages, names, and other odd bits of text.

    oai_token-act-pair · gemini-2.0-flash

    Code, URLs or data

    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
     propOrder
    -0.55
     forState
    -0.54
    saraba
    -0.53
    исленность
    -0.52
    RuleContext
    -0.52
    RegressionTest
    -0.51
     Ause
    -0.50
    ":[{
    -0.50
    crackers
    -0.49
    DrawerToggle
    -0.49
    POSITIVE LOGITS
    ConstraintMaker
    0.72
    eschou
    0.55
    éndole
    0.54
     les
    0.53
    CloseOperation
    0.50
     Smyth
    0.50
     Moura
    0.48
    лте
    0.47
     Horv
    0.46
     Hers
    0.46
    Activations Density 2.263%

    No Known Activations