© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4187
    Prev
    Next
    INDEX
    Explanations

    mentions of 'Type' in code and other text

    oai_token-act-pair · gemini-2.0-flash

    programming type definitions

    np_token-act-pair-logits · gpt-4o-mini

    type

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    évaluateur
    -0.55
     $__
    -0.53
     ni
    -0.50
     ved
    -0.48
    ty
    -0.48
    المراجع
    -0.48
     LoggerFactory
    -0.48
     Weise
    -0.47
    дә
    -0.47
     ma
    -0.46
    POSITIVE LOGITS
     NSCoder
    0.73
     surla
    0.70
    IndentedString
    0.59
    UIControlState
    0.58
     avoient
    0.57
     profeta
    0.56
    mű
    0.55
     ſte
    0.55
     worshipped
    0.54
     étoient
    0.52
    Activations Density 2.488%

    No Known Activations