© 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-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145315
    Prev
    Next
    INDEX
    Explanations

    central to narratives or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    t
    2.42
    in
    2.28
    the
    2.27
    at
    2.23
    i
    2.05
    ar
    1.92
    ten
    1.91
    ta
    1.81
    ty
    1.74
    an
    1.68
    POSITIVE LOGITS
    ير
    1.63
    ’),
    1.58
    كان
    1.55
    <0x0D>
    1.53
    ج
    1.53
     capaces
    1.52
    كمل
    1.46
     alteraciones
    1.45
    يم
    1.44
    ول
    1.42
    Activations Density 0.003%

    No Known Activations