© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 240730
    Prev
    Next
    INDEX
    Explanations

    intermediate results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
     기본
    0.42
     சரா
    0.41
     postural
    0.40
     χαρακτη
    0.40
     윤
    0.40
     მო
    0.39
     개념
    0.39
     posture
    0.39
    껴
    0.39
     சனி
    0.38
    POSITIVE LOGITS
    iderm
    0.41
    restrict
    0.41
     sellers
    0.39
    hidden
    0.38
    seller
    0.38
    other
    0.37
    path
    0.37
    BUTTON
    0.37
    Anonymous
    0.37
    baked
    0.37
    Activations Density 0.001%

    No Known Activations