© 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. 38917
    Prev
    Next
    INDEX
    Explanations

    al sound

    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
    F
    0.59
     F
    0.57
    Fal
    0.57
     FAL
    0.54
     Fa
    0.53
    ฟา
    0.53
    Ф
    0.52
    ฟ
    0.52
     f
    0.52
     фа
    0.52
    POSITIVE LOGITS
    als
    0.50
    alsa
    0.49
    ăl
    0.47
     alk
    0.46
    alka
    0.46
    lex
    0.44
    alse
    0.44
    ounded
    0.43
    alc
    0.42
    olds
    0.42
    Activations Density 0.015%

    No Known Activations