© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 42431
    Prev
    Next
    INDEX
    Explanations

    voyager, magellan, path

    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_13_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
    राबाद
    0.54
    𝐜
    0.54
    ធី
    0.53
     maliciously
    0.53
    니다
    0.52
    StoreID
    0.51
    лизация
    0.50
    اما
    0.50
    ковым
    0.49
    haba
    0.49
    POSITIVE LOGITS
     waterline
    0.54
    imoto
    0.51
     waters
    0.50
    íte
    0.49
    ה
    0.47
    ote
    0.47
    rete
    0.47
    imeter
    0.46
    水
    0.46
    ewater
    0.46
    Activations Density 0.003%

    No Known Activations