© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33572
    Prev
    Next
    INDEX
    Explanations

    Field Day, meat, lamb, fish

    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
    ↵
    0.79
    tu
    0.75
    ts
    0.71
    to
    0.71
    tre
    0.66
    s
    0.62
    top
    0.61
     significant
    0.59
    tb
    0.59
    de
    0.58
    POSITIVE LOGITS
    기
    0.73
    어
    0.71
    ного
    0.70
    ı
    0.70
    ла
    0.69
    وم
    0.68
    য়া
    0.67
    ā
    0.66
     maliciously
    0.65
    ского
    0.64
    Activations Density 0.004%

    No Known Activations