© 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. 111993
    Prev
    Next
    INDEX
    Explanations

    young child

    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
     to
    1.65
    in
    1.52
    ك
    1.51
    a
    1.40
    ка
    1.32
    R
    1.23
    د
    1.22
    an
    1.17
     in
    1.11
    of
    1.11
    POSITIVE LOGITS
    ции
    1.29
    ২০
    1.16
    ación
    1.07
    습니다
    1.05
     сообщи
    1.04
    re
    1.00
     těch
    0.99
    の
    0.97
    ces
    0.96
    ле
    0.96
    Activations Density 0.000%

    No Known Activations