© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57737
    Prev
    Next
    INDEX
    Explanations

    et cetera

    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_59_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
    多
    1.66
    Mult
    1.11
     đa
    1.04
    mult
    1.03
    Multi
    1.02
     multi
    1.00
     Multi
    0.99
     Mult
    0.96
    multi
    0.96
    MULT
    0.94
    POSITIVE LOGITS
    𝙍
    0.48
     ))->
    0.41
     많이
    0.40
    }\|_{
    0.39
     เยอะ
    0.38
     ?",
    0.38
     丿
    0.37
     ссылка
    0.37
     ():
    0.37
     冖
    0.36
    Activations Density 0.020%

    No Known Activations