© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23862
    Prev
    Next
    INDEX
    Explanations

    organize

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    ァ
    0.63
    ォ
    0.52
    ェ
    0.49
    ⿰
    0.47
    ィ
    0.46
    ⿱
    0.44
    eb
    0.41
     complication
    0.41
    ek
    0.39
    ero
    0.39
    POSITIVE LOGITS
    iest
    0.50
    де
    0.46
    aan
    0.44
    יות
    0.44
    aire
    0.43
    y
    0.42
    lı
    0.41
    ius
    0.40
    tet
    0.40
    yka
    0.40
    Activations Density 0.010%

    No Known Activations