© 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. 235600
    Prev
    Next
    INDEX
    Explanations

    github

    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
     Knox
    0.41
     hurdle
    0.36
    orben
    0.36
     വല
    0.35
    akn
    0.35
    setTo
    0.35
     сра
    0.34
    臤
    0.34
    coeff
    0.34
    StrTo
    0.34
    POSITIVE LOGITS
     HENRY
    0.40
     نگر
    0.40
     Gerard
    0.39
    ATOR
    0.39
     Thir
    0.39
    🛐
    0.39
    mlp
    0.38
     рассказа
    0.37
    AGER
    0.37
     MALL
    0.37
    Activations Density 0.000%

    No Known Activations