© 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. 127703
    Prev
    Next
    INDEX
    Explanations

    Campaign Prompt

    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
    使
    0.72
    وي
    0.70
    ал
    0.68
    Datos
    0.68
    Haupt
    0.68
    Prim
    0.65
    ية
    0.65
    К
    0.65
    G
    0.64
    Д
    0.63
    POSITIVE LOGITS
    u
    1.05
    t
    0.81
    ม
    0.68
    UCKY
    0.64
    p
    0.63
     vadati
    0.63
    er
    0.61
     lotta
    0.59
     vattati
    0.58
     sabbam
    0.58
    Activations Density 0.006%

    No Known Activations