© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107266
    Prev
    Next
    INDEX
    Explanations

    Russian terms and descriptions

    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_2_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
    u
    1.23
    '
    1.20
     aument
    1.16
    ¹.
    1.16
    рке
    1.14
     distrib
    1.12
     réduite
    1.12
    '}
    1.10
     enfoque
    1.10
    ج
    1.09
    POSITIVE LOGITS
    al
    1.69
    ى
    1.25
    います
    1.17
    ет
    1.16
    ない
    1.15
    alik
    1.14
    ラ
    1.14
    い
    1.12
    야
    1.11
    です
    1.07
    Activations Density 0.004%

    No Known Activations