© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12132
    Prev
    Next
    INDEX
    Explanations

    angle brackets commonly used in code

    oai_token-act-pair · gemini-2.0-flash

    Code-like text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    àm
    -0.47
    сар
    -0.46
     Например
    -0.45
     ejemplo
    -0.43
     частности
    -0.43
    ider
    -0.42
     például
    -0.42
    приклад
    -0.41
     eksempel
    -0.41
    たとえば
    -0.41
    POSITIVE LOGITS
    adaptiveStyles
    0.75
    EndGlobalSection
    0.69
     ModelExpression
    0.69
    enterOuterAlt
    0.68
     незавершена
    0.67
     تضيفلها
    0.67
    oa̍t
    0.66
     <>",
    0.66
    
    0.66
    OGND
    0.65
    Activations Density 1.183%

    No Known Activations