© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 142113
    Prev
    Next
    INDEX
    Explanations

    in

    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_46_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
     menggunakan
    0.43
     determined
    0.42
    輩
    0.42
     using
    0.40
    essels
    0.40
     emerged
    0.39
    determined
    0.39
    decimals
    0.39
     Wechsler
    0.38
    tbLabel
    0.38
    POSITIVE LOGITS
    اتے
    0.39
     សូម
    0.38
    楚
    0.38
     functional
    0.37
     ကု
    0.37
     afectadas
    0.36
    celona
    0.36
    lation
    0.35
    万人
    0.35
     callers
    0.35
    Activations Density 0.002%

    No Known Activations