© 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. 6056
    Prev
    Next
    INDEX
    Explanations

    the word "by" and related website structural elements like '//' and '.'.

    oai_token-act-pair · 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
     John
    -0.81
     Michael
    -0.76
    John
    -0.76
     Richard
    -0.75
     Tom
    -0.75
     Steve
    -0.74
     Andrew
    -0.73
     David
    -0.72
     Sarah
    -0.71
     Jason
    -0.71
    POSITIVE LOGITS
    ValueStyle
    0.54
    AccessorTable
    0.52
     gainera
    0.51
    adaptiveStyles
    0.51
     ExecuteAsync
    0.47
     OMITBAD
    0.46
     HasFactory
    0.46
    LEncoder
    0.45
    IntoConstraints
    0.45
    Попис
    0.45
    Activations Density 2.483%

    No Known Activations