© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8722
    Prev
    Next
    INDEX
    Explanations

    empirical evidence and studies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     осе
    2.61
    器的
    2.57
    quả
    2.29
     координат
    2.28
    로
    2.28
    <unused40>
    2.25
    ع
    2.22
    xious
    2.20
     maliciously
    2.17
    @[
    2.16
    POSITIVE LOGITS
    nement
    2.56
    طور
    2.55
    on
    2.47
     mutagenesis
    2.36
    ط
    2.33
    كب
    2.31
    een
    2.29
    েন
    2.27
     fato
    2.25
    re
    2.24
    Activations Density 0.032%

    No Known Activations