© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14307
    Prev
    Next
    INDEX
    Explanations

    copyright notices, function definitions and risk assessment descriptions.

    oai_token-act-pair · gemini-2.0-flash

    code, tech, academic writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    脚注の使い方
    -0.75
    CrossRef
    -0.63
    TextWatcher
    -0.63
    DoubleQuotes
    -0.60
    Tembelea
    -0.57
    InstanceState
    -0.54
     nonatomic
    -0.54
    ReusableCell
    -0.54
    enumii
    -0.54
    WRENCE
    -0.54
    POSITIVE LOGITS
    <bos>
    2.02
     Efq
    0.59
     himſelf
    0.54
     itſelf
    0.52
    .*")]
    0.52
     fhew
    0.52
     Houſe
    0.52
     Jefus
    0.50
     myſelf
    0.49
     theſe
    0.49
    Activations Density 7.252%

    No Known Activations