© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171131
    Prev
    Next
    INDEX
    Explanations

    field of study or discipline

    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_20_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
    а
    0.22
    ра
    0.17
    z
    0.17
    sh
    0.17
    bff
    0.17
    p
    0.17
    п
    0.17
    че
    0.17
    ങ്ങ
    0.17
    3
    0.16
    POSITIVE LOGITS
    ｢
    0.17
     genetic
    0.16
    的方法
    0.16
     کە
    0.16
     ƯCLN
    0.16
    zechos
    0.16
    「
    0.16
    dimethyl
    0.16
     columns
    0.16
     expériences
    0.16
    Activations Density 0.040%

    No Known Activations