© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27631
    Prev
    Next
    INDEX
    Explanations

    pf

    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_10_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
    ↵
    0.19
    to
    0.19
    (
    0.18
    u
    0.16
    ल
    0.16
    、
    0.16
    -
    0.15
    )(
    0.14
    l
    0.14
    ，
    0.14
    POSITIVE LOGITS
     Вот
    0.14
     VStack
    0.14
    angleright
    0.13
    cknowledg
    0.13
     multival
    0.13
     Какой
    0.13
    пропетров
    0.13
     Очень
    0.12
    ீர்க
    0.12
    VSLU
    0.12
    Activations Density 0.009%

    No Known Activations