© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37454
    Prev
    Next
    INDEX
    Explanations

    Shrinking

    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
    ać
    0.43
    rescence
    0.42
    াচার্য
    0.41
    rene
    0.40
    ality
    0.40
    ષ
    0.39
    zzel
    0.38
    ző
    0.38
    宛
    0.38
    zeum
    0.38
    POSITIVE LOGITS
    आपका
    0.39
     nk
    0.37
     Leonardo
    0.37
    Cub
    0.37
    нак
    0.36
     والر
    0.36
    숩
    0.35
     FLOOR
    0.35
    Კ
    0.35
     Angular
    0.35
    Activations Density 0.000%

    No Known Activations