© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90653
    Prev
    Next
    INDEX
    Explanations

    allem

    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_11_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
    elt
    0.66
    公
    0.66
    Public
    0.65
    pp
    0.64
    if
    0.61
     as
    0.61
    public
    0.61
    bb
    0.60
    BB
    0.59
    xx
    0.59
    POSITIVE LOGITS
     കാണ
    0.65
    ходы
    0.64
     dehydrogenase
    0.63
     коэффициент
    0.62
    ল
    0.62
     ও
    0.61
     *}
    0.61
    TISE
    0.61
     anastom
    0.61
    ກ
    0.61
    Activations Density 0.000%

    No Known Activations