© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7000
    Prev
    Next
    INDEX
    Explanations

    punctuation and word starts

    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_39_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
     Álvarez
    0.41
     Ä
    0.38
     sätt
    0.38
    ഴ്ച
    0.37
     Nore
    0.36
    របស់យើង
    0.36
    ല്ല
    0.34
    𒋢
    0.34
    ళ్ళ
    0.34
    人們
    0.34
    POSITIVE LOGITS
     conti
    0.52
     investi
    0.52
    蜘
    0.51
     উপজে
    0.49
     construc
    0.48
     whi
    0.48
     അദ്ദേ
    0.48
     combina
    0.48
     organi
    0.48
     Elec
    0.47
    Activations Density 0.136%

    No Known Activations