© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 210355
    Prev
    Next
    INDEX
    Explanations

    aware

    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_10_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
    кі
    0.35
    ائرة
    0.35
    ্যের
    0.33
    '
    0.33
    ين
    0.32
    τητα
    0.31
    istema
    0.31
    ков
    0.30
    ким
    0.30
    flight
    0.30
    POSITIVE LOGITS
     organisme
    0.39
     this
    0.38
     অ্যাক
    0.37
     avances
    0.37
    u
    0.36
    ről
    0.36
     légumes
    0.36
     you
    0.35
    nent
    0.35
     huts
    0.35
    Activations Density 0.032%

    No Known Activations