© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45571
    Prev
    Next
    INDEX
    Explanations

    giving thanks

    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_3_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
    он
    0.75
    '
    0.72
    0.72
    .
    0.70
    ↵
    0.70
    ме
    0.69
    jší
    0.67
     будет
    0.66
     variar
    0.66
    ing
    0.65
    POSITIVE LOGITS
    t
    0.97
    y
    0.91
    ן
    0.78
    Ϣ
    0.75
    AVG
    0.74
    AAA
    0.73
    IN
    0.73
    Ṣ
    0.73
    AIR
    0.71
    მასრულ
    0.70
    Activations Density 0.000%

    No Known Activations