© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31578
    Prev
    Next
    INDEX
    Explanations

    nominated by

    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_31_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
     escalera
    0.41
    枡
    0.39
     McIntosh
    0.38
    ეთის
    0.38
    電圧
    0.38
     arus
    0.38
     solids
    0.36
     дверей
    0.36
     herzlich
    0.36
    子が
    0.35
    POSITIVE LOGITS
     بأن
    0.38
    ક્ષા
    0.37
    サイクル
    0.36
    stat
    0.36
     काला
    0.35
    ତ
    0.35
    হান
    0.35
     VU
    0.35
    锑
    0.35
    Hor
    0.34
    Activations Density 0.019%

    No Known Activations