© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 142156
    Prev
    Next
    INDEX
    Explanations

    crowdfunding

    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
     좌
    0.28
    州市
    0.27
    [multimodal]
    0.27
    UNDS
    0.27
    Linq
    0.25
     yöntem
    0.25
     രണ്ടു
    0.25
     електро
    0.25
    ються
    0.24
    Interfaz
    0.24
    POSITIVE LOGITS
    ش
    0.29
     کە
    0.28
     شوي
    0.28
     Laure
    0.28
    য়া
    0.27
    يو
    0.27
    cdr
    0.27
    ra
    0.27
    شو
    0.27
    scor
    0.26
    Activations Density 0.000%

    No Known Activations