© 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. 206223
    Prev
    Next
    INDEX
    Explanations

    holding close

    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
     );
    0.22
     थोड़े
    0.21
    ("*
    0.20
     broadest
    0.20
     --
    0.20
    验证
    0.19
    ίου
    0.19
     est
    0.19
    已經
    0.19
     r
    0.18
    POSITIVE LOGITS
    ್ಧ
    0.24
    tering
    0.24
    Де
    0.23
    {,}
    0.23
    JK
    0.23
    zut
    0.23
    sorption
    0.22
    Chhattisgarh
    0.22
    До
    0.22
    facing
    0.22
    Activations Density 0.003%

    No Known Activations