© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16349
    Prev
    Next
    INDEX
    Explanations

    the "sc" word fragment

    oai_token-act-pair · gemini-2.0-flash

    Scotian Shelf/Scopes Trial

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Šaltiniai
    -0.70
     ExecuteAsync
    -0.69
    
    -0.69
    Referencies
    -0.68
    PerformLayout
    -0.67
    AutoScaleMode
    -0.67
     оригіналу
    -0.66
    addCriterion
    -0.65
    MENAFN
    -0.60
    ForValue
    -0.59
    POSITIVE LOGITS
    Lap
    0.45
     ModelExpression
    0.45
    yarnpkg
    0.44
     Pilate
    0.42
    wl
    0.42
    lap
    0.42
     الحره
    0.41
     fér
    0.41
    InstanceState
    0.40
    fly
    0.40
    Activations Density 1.322%

    No Known Activations