© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36907
    Prev
    Next
    INDEX
    Explanations

    a wealth of

    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_11_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
    z
    0.61
    h
    0.61
    ง
    0.61
    вной
    0.58
    zj
    0.57
    CRUD
    0.56
    Ⴀ
    0.55
    élim
    0.54
    푞
    0.54
    saxophone
    0.54
    POSITIVE LOGITS
    ’
    0.70
     predom
    0.64
     ili
    0.61
     பார்வை
    0.59
     призна
    0.55
    ized
    0.55
     tarafından
    0.54
     MTLTexture
    0.54
    arrison
    0.53
     Rajya
    0.53
    Activations Density 0.001%

    No Known Activations