© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201837
    Prev
    Next
    INDEX
    Explanations

    TrueNAS SCALE

    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_12_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
    pR
    0.21
    $
    0.20
    p
    0.20
    chh
    0.18
    pr
    0.18
    ching
    0.18
     प्रभावित
    0.18
     ਪ
    0.18
     ਇਕ
    0.18
    pa
    0.18
    POSITIVE LOGITS
     izan
    0.19
     jungen
    0.19
    瑭
    0.19
     Möglich
    0.18
     princesa
    0.18
     lehet
    0.18
     malle
    0.18
    우
    0.18
     njen
    0.18
     fiddle
    0.18
    Activations Density 0.001%

    No Known Activations