© 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-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57582
    Prev
    Next
    INDEX
    Explanations

    frequency

    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
    ’
    1.10
    withProperties
    0.66
    that
    0.63
     يؤ
    0.63
     vozila
    0.63
     svak
    0.61
     wcex
    0.60
     Were
    0.59
     negeri
    0.59
     społecz
    0.58
    POSITIVE LOGITS
    i
    0.92
    an
    0.81
    in
    0.75
    m
    0.73
    و
    0.72
    マ
    0.64
    ne
    0.64
    el
    0.64
    con
    0.63
    en
    0.61
    Activations Density 0.019%

    No Known Activations