© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 216044
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers

    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_50_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
    ;
    0.39
     SV
    0.39
     devant
    0.39
     pant
    0.37
    стви
    0.37
    raft
    0.37
    soa
    0.36
    νος
    0.36
     συνα
    0.36
    oting
    0.35
    POSITIVE LOGITS
    لع
    0.42
    Eu
    0.41
    ##
    0.39
     Smy
    0.39
    Ey
    0.38
    Ei
    0.38
     Бү
    0.38
     ئ
    0.37
     Sacchar
    0.37
    eid
    0.37
    Activations Density 0.001%

    No Known Activations