© 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. 38890
    Prev
    Next
    INDEX
    Explanations

    or

    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
    folge
    0.40
    Ｍ
    0.38
    𒆳
    0.35
    nului
    0.35
    োপ
    0.34
    copyWith
    0.34
    ments
    0.34
    ńskiego
    0.34
    𝖒
    0.34
     portions
    0.33
    POSITIVE LOGITS
     more
    0.70
     many
    0.70
     بسیاری
    0.70
     многие
    0.68
    many
    0.67
     많은
    0.66
    Many
    0.65
     više
    0.64
     أكثر
    0.64
     muitas
    0.63
    Activations Density 0.003%

    No Known Activations