© 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. 161813
    Prev
    Next
    INDEX
    Explanations

    trailing phrases

    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
     on
    1.40
    其他
    1.40
    is
    1.35
    يا
    1.34
    </h2>
    1.18
    お
    1.16
    in
    1.13
    л
    1.11
    د
    1.11
     or
    1.10
    POSITIVE LOGITS
    ne
    1.35
    ü
    1.16
    ित
    1.16
    ill
    1.13
     been
    1.12
    ۰
    1.11
    ри
    1.10
    ва
    1.08
    iz
    1.07
    tex
    1.06
    Activations Density 0.001%

    No Known Activations