© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 81810
    Prev
    Next
    INDEX
    Explanations

    say "----------------"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
     ipc
    0.38
     Alonzo
    0.38
     Pelham
    0.37
     Understand
    0.37
     McGr
    0.37
    ผู้ตัดสิน
    0.36
    }`));
    0.36
     תח
    0.36
     pel
    0.35
    utch
    0.35
    POSITIVE LOGITS
     Extensive
    0.38
    ^{*}=
    0.37
    AND
    0.37
     nos
    0.36
     Nos
    0.36
     prede
    0.35
    *=
    0.35
     ITEMIZED
    0.35
    oare
    0.35
     consents
    0.34
    Activations Density 0.002%

    No Known Activations