© 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. 130633
    Prev
    Next
    INDEX
    Explanations

    -minded, -inspired, -oriented, -layered

    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
    م
    1.34
    ن
    1.19
    ン
    1.04
    ส
    0.98
    酺
    0.91
     to
    0.88
    ен
    0.87
    :',
    0.87
    د
    0.87
    ЕТ
    0.86
    POSITIVE LOGITS
    is
    1.55
    ↵
    1.43
    h
    1.39
    c
    1.39
    u
    1.39
    x
    1.28
    t
    1.26
    s
    1.24
    y
    1.22
    a
    1.20
    Activations Density 0.002%

    No Known Activations