© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246172
    Prev
    Next
    INDEX
    Explanations

    conventional commits

    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_40_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
     hus
    0.41
    eas
    0.38
    яр
    0.38
    众
    0.38
     miro
    0.37
    ovane
    0.37
    ione
    0.36
     javax
    0.36
    зел
    0.36
     alteration
    0.35
    POSITIVE LOGITS
    centaje
    0.41
    uldade
    0.38
     طويلة
    0.38
    ཾ
    0.37
     [§
    0.37
    ("|
    0.37
     অক্টো
    0.37
    orkel
    0.37
    annten
    0.36
    organiser
    0.36
    Activations Density 0.000%

    No Known Activations