© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39947
    Prev
    Next
    INDEX
    Explanations

    US

    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_57_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
    Ch
    0.44
     ch
    0.43
     Ch
    0.42
    <0xAE>
    0.42
    aik
    0.40
    ogliere
    0.40
     ч
    0.40
    дав
    0.40
    ights
    0.39
    ITIES
    0.38
    POSITIVE LOGITS
     Tr
    0.50
    苍
    0.42
     ta
    0.41
     Trustees
    0.39
     str
    0.39
     Tans
    0.39
     Ababa
    0.39
    Exp
    0.38
     സ്ഥ
    0.38
     Abr
    0.38
    Activations Density 0.000%

    No Known Activations