© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108000
    Prev
    Next
    INDEX
    Explanations

    ive, wa, Givaudan, CIWS

    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_2_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
    '
    1.63
    AN
    1.59
    AR
    1.53
    N
    1.47
    V
    1.42
    H
    1.41
    W
    1.38
    は
    1.38
    K
    1.34
    는
    1.32
    POSITIVE LOGITS
    ن
    1.44
     for
    1.07
    ва
    1.07
    νει
    1.00
    رات
    0.99
    ación
    0.99
    بي
    0.98
    ش
    0.98
     ожида
    0.97
    és
    0.96
    Activations Density 0.000%

    No Known Activations