© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9525
    Prev
    Next
    INDEX
    Explanations

    cob, dob, DB

    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
    검
    0.41
     Wast
    0.38
     SMO
    0.37
    anut
    0.37
    avax
    0.36
    Hence
    0.36
    ometers
    0.36
    idel
    0.35
     Exams
    0.35
    கிழ
    0.35
    POSITIVE LOGITS
    ニーズ
    0.39
     dob
    0.38
     currentPlayer
    0.38
    髒
    0.38
     dogs
    0.37
     carta
    0.37
     curses
    0.36
     thirsty
    0.36
     cursed
    0.35
    碇
    0.35
    Activations Density 0.046%

    No Known Activations