© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 8301
    Prev
    Next
    INDEX
    Explanations

    locations or containers

    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
     table
    -0.85
    table
    -0.75
     stall
    -0.74
    AsUp
    -0.73
    InitVars
    -0.72
    Portale
    -0.71
     booth
    -0.68
     Table
    -0.68
     seat
    -0.65
    ')):
    -0.60
    POSITIVE LOGITS
     bun
    0.63
    bigoplus
    0.54
    endphp
    0.52
     оригіналу
    0.50
     ham
    0.49
    ksikon
    0.48
    istoitu
    0.47
    kelijkheid
    0.47
    BeginContext
    0.45
     محفوظة
    0.45
    Activations Density 5.043%

    No Known Activations