© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132310
    Prev
    Next
    INDEX
    Explanations

    subversion

    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
    人
    1.43
    한
    1.16
    ин
    1.09
    인
    1.06
    الإ
    1.02
    İ
    0.99
    お金
    0.96
    أ
    0.95
    ан
    0.94
    أت
    0.94
    POSITIVE LOGITS
    o
    1.42
    y
    1.34
    her
    1.16
    z
    1.13
    ver
    1.13
    us
    1.07
    k
    1.05
    many
    1.02
    u
    1.02
    r
    1.01
    Activations Density 0.000%

    No Known Activations