© 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. 4219
    Prev
    Next
    INDEX
    Explanations

    code snippets containing C++, Javascript or similar programming languages

    oai_token-act-pair · gemini-2.0-flash

    scope

    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
     Scope
    -2.33
     scope
    -2.31
    Scope
    -2.28
    scope
    -2.27
     scopes
    -2.06
     SCOPE
    -2.00
    SCOPE
    -1.95
     span
    -1.84
     spans
    -1.73
    scopes
    -1.62
    POSITIVE LOGITS
    Diweddarwch
    0.59
    Autoritní
    0.59
     betweenstory
    0.56
    Jereo
    0.50
     initComponents
    0.49
    RegressionTest
    0.49
     Biôgrafia
    0.48
    extAlignment
    0.47
    SerializedName
    0.47
    phism
    0.47
    Activations Density 2.188%

    No Known Activations