© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 57881
    Prev
    Next
    INDEX
    Explanations

    format,òria, formació

    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_2_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
    ی
    1.49
    ني
    1.32
     ajout
    1.23
    ન
    1.23
    К
    1.22
    ກະ
    1.16
    もの
    1.16
    רים
    1.16
    ς
    1.14
    ن
    1.12
    POSITIVE LOGITS
    f
    1.73
    ä
    1.48
    ى
    1.44
    ang
    1.20
    ong
    1.16
    <0x80>
    1.15
    vä
    1.09
    1
    1.05
    é
    1.05
     Championship
    1.03
    Activations Density 0.000%

    No Known Activations