© 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. 107915
    Prev
    Next
    INDEX
    Explanations

    concierge services

    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
     for
    1.63
    d
    1.52
    ุ
    1.35
    don
    1.27
    dog
    1.20
    ع
    1.14
    o
    1.09
    m
    1.09
    man
    1.05
    for
    1.03
    POSITIVE LOGITS
    你
    1.41
    ۹
    1.33
    (
    1.27
    습니다
    1.15
    1.14
    На
    1.12
    Для
    1.10
    도
    1.08
    6
    1.05
    "
    1.05
    Activations Density 0.001%

    No Known Activations