© 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. 8913
    Prev
    Next
    INDEX
    Explanations

    terminology related to 3D printing, computer programming, and cellular frequencies

    oai_token-act-pair · gemini-2.0-flash

    French technical conversations

    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
     kaynağından
    -0.69
    ********/
    -0.52
    kháu
    -0.52
     itſelf
    -0.51
    جراء
    -0.50
    istisches
    -0.49
    GeneratedMessage
    -0.48
    iour
    -0.48
     بتاريخ
    -0.48
    不成
    -0.48
    POSITIVE LOGITS
    XtraReports
    0.63
    ]._
    0.52
    enite
    0.51
     HasFactory
    0.50
    ]){
    0.49
    ọa
    0.49
    VersionUID
    0.48
    Diwedd
    0.48
    specialchars
    0.48
    ')(
    0.47
    Activations Density 0.985%

    No Known Activations