© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11238
    Prev
    Next
    INDEX
    Explanations

    a mix of elements including code snippets, elements from technical documentation, and formatting/spacing indicators.

    oai_token-act-pair · gemini-2.0-flash

    Electrical components

    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
    mar
    -0.46
    utella
    -0.45
    styleType
    -0.44
     mar
    -0.44
     pay
    -0.41
    utica
    -0.39
     незавершена
    -0.39
     pes
    -0.39
    paid
    -0.38
     Mar
    -0.38
    POSITIVE LOGITS
    олові
    0.75
     ويكيپيديا
    0.71
    bootstrapcdn
    0.68
    himovic
    0.65
    quième
    0.64
     TextAppearance
    0.63
    ConstraintMaker
    0.63
     يتيمه
    0.63
     Theſe
    0.62
     citoy
    0.61
    Activations Density 3.054%

    No Known Activations