© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 113020
    Prev
    Next
    INDEX
    Explanations

    control / uncontrol

    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
    ק
    1.13
    ח
    1.13
    "];
    1.05
    א
    1.05
    ש
    1.04
    لا
    1.00
    רו
    0.96
     използва
    0.96
    </td>
    0.96
    );
    0.96
    POSITIVE LOGITS
    as
    1.23
    ade
    1.18
    el
    1.13
    ed
    1.11
    et
    1.09
    ów
    1.05
    िंग
    1.05
    eleng
    1.04
    be
    1.03
    ci
    1.02
    Activations Density 0.001%

    No Known Activations