© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44442
    Prev
    Next
    INDEX
    Explanations

    COLOR conversion

    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_22_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
     Ayurvedic
    0.18
    iffness
    0.17
    nostic
    0.16
     Stewardship
    0.15
     erythemat
    0.15
     Cinemas
    0.15
     stew
    0.14
     (=
    0.14
    PTMR
    0.14
    所在地
    0.14
    POSITIVE LOGITS
     оф
    0.16
     ва
    0.15
     bagging
    0.14
    แบ
    0.14
    フロ
    0.14
    ંપની
    0.14
     гаран
    0.14
     иң
    0.14
     bul
    0.14
     безо
    0.13
    Activations Density 0.003%

    No Known Activations