© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 207238
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    порта
    0.25
     mediante
    0.25
    czaj
    0.25
    }$\
    0.24
     ⠀
    0.24
    卓越
    0.24
    घाटन
    0.24
     busting
    0.24
    }.\
    0.24
    ळा
    0.23
    POSITIVE LOGITS
     kind
    0.24
     lait
    0.23
    มนเชสเตอร์
    0.23
     Ce
    0.23
     sous
    0.23
     differentially
    0.23
    Said
    0.23
     Manual
    0.23
     Kee
    0.23
     talk
    0.23
    Activations Density 0.001%

    No Known Activations