© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1562
    Prev
    Next
    INDEX
    Explanations

    to [action verb]

    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_40_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
     raven
    0.17
    綴
    0.17
     कहें
    0.17
     Sec
    0.17
     ё
    0.16
     picnic
    0.16
    rapie
    0.16
     Se
    0.16
     trabaj
    0.16
    叫
    0.16
    POSITIVE LOGITS
     haies
    0.17
    ਜ
    0.16
     undertook
    0.16
     couldn
    0.16
     attempted
    0.16
     tapped
    0.16
    မဟုတ်
    0.16
     created
    0.16
     možete
    0.16
     didn
    0.15
    Activations Density 0.263%

    No Known Activations