© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129201
    Prev
    Next
    INDEX
    Explanations

    why

    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
    a
    1.04
    ه
    1.02
    н
    1.01
    ၿ
    0.96
    ی
    0.85
    ا
    0.83
    ン
    0.82
     филосо
    0.82
    ה
    0.81
    ১০
    0.80
    POSITIVE LOGITS
    ade
    1.23
    ina
    1.20
    ang
    1.20
    ando
    1.13
    anga
    1.11
    iro
    1.10
    ist
    1.09
    ere
    1.09
    uj
    1.06
    ard
    1.03
    Activations Density 0.005%

    No Known Activations