© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133672
    Prev
    Next
    INDEX
    Explanations

    educative.io

    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_6_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
    ना
    1.07
    ما
    0.98
    nés
    0.97
    Да
    0.93
    (
    0.91
    '
    0.91
    ップ
    0.90
    セ
    0.89
    Соцмережа
    0.89
     эпоху
    0.88
    POSITIVE LOGITS
    t
    1.44
    ί
    1.01
    c
    1.00
    d
    0.96
    st
    0.90
    р
    0.89
    anting
    0.87
    dU
    0.86
    0.85
    E
    0.84
    Activations Density 0.000%

    No Known Activations