© 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. 6918
    Prev
    Next
    INDEX
    Explanations

    numbers and units of time or currency

    oai_token-act-pair · gemini-2.0-flash

    Numbers and quantities in context

    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
     يتيمه
    -0.55
     NSCoder
    -0.52
    GraphicsUnit
    -0.52
    formik
    -0.52
     avoient
    -0.48
    SetString
    -0.48
     jorden
    -0.47
    LogManager
    -0.47
    coration
    -0.47
    WebVitals
    -0.47
    POSITIVE LOGITS
    EndInit
    0.54
    principalTable
    0.50
    utives
    0.50
    intios
    0.48
    rawDesc
    0.47
    écial
    0.47
     *)__
    0.46
    )}.
    0.46
    êques
    0.46
    hasErrors
    0.45
    Activations Density 22.905%

    No Known Activations