© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 207991
    Prev
    Next
    INDEX
    Explanations

    contrast connectors

    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_56_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
     Fakat
    0.46
    }$;
    0.46
    )$;
    0.42
    ；
    0.42
    ();
    0.41
    °;
    0.40
    \";
    0.38
    ;
    0.38
    ）；
    0.38
    ؛
    0.38
    POSITIVE LOGITS
     ov
    1.06
     Ov
    0.82
     OV
    0.74
    Ov
    0.74
    tet
    0.70
    Tet
    0.68
     tet
    0.65
     Akan
    0.63
     Will
    0.60
    Will
    0.59
    Activations Density 0.002%

    No Known Activations