© 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. 90974
    Prev
    Next
    INDEX
    Explanations

    должен/должна/должно

    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
     dakkh
    0.75
     vuccanti
    0.71
    ע
    0.71
    จะ
    0.70
     patitth
    0.70
     aparent
    0.69
    apayati
    0.68
     baseApiPath
    0.68
     windfall
    0.68
     instill
    0.67
    POSITIVE LOGITS
    ’
    0.84
    wys
    0.68
    <
    0.67
    Ad
    0.66
    umm
    0.66
    ado
    0.65
    ão
    0.65
    Bench
    0.64
    Client
    0.63
    Schemas
    0.63
    Activations Density 0.001%

    No Known Activations