© 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. 3773
    Prev
    Next
    INDEX
    Explanations

    technical jargon and identifiers

    oai_token-act-pair · gemini-2.0-flash

    technical forum discussions

    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
     continúas
    -0.66
    djangoproject
    -0.65
    Manbalar
    -0.60
     figliu
    -0.58
     enfans
    -0.56
    NewUrlParser
    -0.54
    createCanvas
    -0.53
     opérés
    -0.53
     répondit
    -0.52
    曖昧さ回避
    -0.51
    POSITIVE LOGITS
    TagMode
    0.55
     ModelExpression
    0.54
     forks
    0.50
     coughing
    0.49
     nightmares
    0.49
    Bricks
    0.48
    unhofer
    0.48
     Forks
    0.48
    copter
    0.48
     bricks
    0.47
    Activations Density 28.238%

    No Known Activations