© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143197
    Prev
    Next
    INDEX
    Explanations

    ismatch, mismatch behavior

    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_0_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
    ла
    1.41
    O
    1.41
    im
    1.26
    6
    1.26
    ل
    1.23
    T
    1.13
    E
    1.09
    4
    1.03
    ad
    1.02
     není
    1.02
    POSITIVE LOGITS
    tions
    1.42
    هم
    1.41
    e
    1.39
    t
    1.34
    h
    1.32
    ال
    1.30
    한
    1.30
    m
    1.28
    ı
    1.28
    个
    1.24
    Activations Density 0.000%

    No Known Activations