© 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. 7892
    Prev
    Next
    INDEX
    Explanations

    the end of sentences, and the start of phrases/clauses

    oai_token-act-pair · gemini-2.0-flash

    listing reasons

    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
     first
    -3.25
    first
    -2.84
    First
    -2.20
     FIRST
    -2.13
     first
    -2.09
    FIRST
    -2.00
     First
    -1.93
     eerste
    -1.92
     primeiro
    -1.88
     ersten
    -1.86
    POSITIVE LOGITS
    migrationBuilder
    0.83
     للاسماء
    0.83
    Билгалдахарш
    0.75
    
    0.70
    DotNetBar
    0.70
    theoremstyle
    0.65
    IonicModule
    0.64
    complexContent
    0.63
     BoxDecoration
    0.62
    addPreferredGap
    0.62
    Activations Density 4.096%

    No Known Activations