© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1277
    Prev
    Next
    INDEX
    Explanations

    kernel info messages

    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_39_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
     ukuran
    0.44
    မိ
    0.44
     seventy
    0.42
     kich
    0.42
     telescopic
    0.41
     size
    0.41
     eighty
    0.41
    >:</
    0.41
    ksz
    0.40
     tamanho
    0.40
    POSITIVE LOGITS
    ань
    0.39
     Accompl
    0.38
    бран
    0.37
     Impacts
    0.36
    /#
    0.36
    anting
    0.35
    ulter
    0.35
     六
    0.34
     Nay
    0.34
    ListenAnd
    0.33
    Activations Density 0.002%

    No Known Activations