© 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. 40820
    Prev
    Next
    INDEX
    Explanations

    groups of people

    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
    for
    0.54
    ك
    0.53
    er
    0.49
    its
    0.47
    if
    0.46
    well
    0.46
    where
    0.45
    market
    0.45
    roles
    0.44
    et
    0.44
    POSITIVE LOGITS
     natthi
    0.45
     SUCH
    0.42
     доктор
    0.41
     desiderio
    0.41
     disappro
    0.40
     Abschnitt
    0.39
    일리
    0.38
    琇
    0.38
     desempeño
    0.38
    百家乐
    0.38
    Activations Density 0.016%

    No Known Activations