© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60406
    Prev
    Next
    INDEX
    Explanations

    van or an

    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
    '
    2.02
    та
    1.46
    на
    1.43
    ش
    1.27
    is
    1.25
    в
    1.18
    то
    1.15
    ন
    1.15
    UR
    1.13
    นะ
    1.10
    POSITIVE LOGITS
     on
    1.63
    ä
    1.41
    inį
    1.09
     It
    0.98
    เล
    0.98
    in
    0.95
    bolic
    0.91
    ling
    0.90
     for
    0.84
    其他
    0.84
    Activations Density 0.001%

    No Known Activations