© 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. 6733
    Prev
    Next
    INDEX
    Explanations

    conditional words like when, if, but, can, and so

    oai_token-act-pair · gemini-2.0-flash

    say "I"

    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
     im
    -1.46
    Im
    -1.30
     Im
    -1.26
    im
    -1.16
     ill
    -1.05
     Ill
    -0.91
    Ill
    -0.90
     IM
    -0.82
    IM
    -0.82
     id
    -0.82
    POSITIVE LOGITS
     I
    1.67
    XmlAccessType
    0.75
    期刊论文
    0.68
    Rüyada
    0.65
    TypedDataSet
    0.63
    localctx
    0.62
     मैंने
    0.60
    bootstrapcdn
    0.59
    FXMLLoader
    0.59
    DataAnnotations
    0.59
    Activations Density 2.685%

    No Known Activations