© 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. 9012
    Prev
    Next
    INDEX
    Explanations

    references to books or stories and positive reactions to them.

    oai_token-act-pair · gemini-2.0-flash

    book content

    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
    tagHelperRunner
    -0.88
    
    -0.81
    脚注の使い方
    -0.78
    rungsseite
    -0.74
     समीक्षाओं
    -0.68
    really
    -0.68
    AutoresizingMask
    -0.67
    AxisAlignment
    -0.65
    Datuak
    -0.65
     الحره
    -0.65
    POSITIVE LOGITS
    EDU
    0.44
     Adam
    0.41
    WireFormatLite
    0.39
    SourceChecksum
    0.39
    colar
    0.38
    uertos
    0.37
     Col
    0.37
    Adam
    0.37
    ifier
    0.36
    >{@
    0.36
    Activations Density 7.287%

    No Known Activations