© 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. 12109
    Prev
    Next
    INDEX
    Explanations

    Java code declaring static final variables

    oai_token-act-pair · gemini-2.0-flash

    static

    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
     static
    -0.70
    static
    -0.56
     revenir
    -0.42
     étranger
    -0.42
     so
    -0.42
    čo
    -0.42
    plin
    -0.42
     our
    -0.40
     noter
    -0.40
    静态
    -0.40
    POSITIVE LOGITS
     iprot
    0.82
     Roskov
    0.74
    ResponseWriter
    0.74
    DockStyle
    0.73
     فريبيس
    0.68
    #+#
    0.68
    matchCondition
    0.68
     gyhoeddwyd
    0.66
     surla
    0.66
    évaluateur
    0.65
    Activations Density 0.227%

    No Known Activations