© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23992
    Prev
    Next
    INDEX
    Explanations

    numbers

    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_56_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
    h
    0.75
     h
    0.75
    ห
    0.60
    ｈ
    0.58
     হ
    0.57
    ℎ
    0.56
     ه
    0.55
    ह
    0.52
    hilt
    0.49
    𝒉
    0.47
    POSITIVE LOGITS
     trou
    0.41
     showed
    0.41
    SD
    0.40
     show
    0.37
    目が
    0.36
    ቸውን
    0.36
     sdl
    0.35
    uyu
    0.35
     days
    0.34
     hours
    0.34
    Activations Density 0.003%

    No Known Activations