© 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. 8978
    Prev
    Next
    INDEX
    Explanations

    words indicating change, time, and past events.

    oai_token-act-pair · gemini-2.0-flash

    Time duration

    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
     SINCE
    -0.69
     Since
    -0.67
    Since
    -0.65
     Because
    -0.64
    Because
    -0.62
    since
    -0.60
     Depuis
    -0.59
     This
    -0.57
    This
    -0.56
    THIS
    -0.52
    POSITIVE LOGITS
    migrationBuilder
    0.96
    +#+#
    0.91
    adaptiveStyles
    0.88
     EconPapers
    0.81
    WebVitals
    0.80
    SequentialGroup
    0.78
    WriteBarrier
    0.76
    enterOuterAlt
    0.76
    AsUp
    0.76
    oredCriteria
    0.74
    Activations Density 27.345%

    No Known Activations