© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170609
    Prev
    Next
    INDEX
    Explanations

    invite-only, selective

    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_20_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
    Stack
    0.44
     También
    0.43
    P
    0.41
     Backpack
    0.40
     य
    0.40
     Przy
    0.40
     Yine
    0.39
     UPS
    0.39
     上
    0.38
    AssignableFrom
    0.38
    POSITIVE LOGITS
    istencia
    0.43
     Farrar
    0.41
    PHA
    0.40
     androgen
    0.40
    itet
    0.39
     vorgesch
    0.39
    fecture
    0.39
     overt
    0.38
     coping
    0.38
    ிற்ப
    0.38
    Activations Density 0.002%

    No Known Activations