© 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. 236057
    Prev
    Next
    INDEX
    Explanations

    Lexus RX

    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
    gax
    0.44
     nargs
    0.43
    leqslant
    0.38
     Braves
    0.37
     Idle
    0.37
    ീഷ
    0.36
    चिंत
    0.36
    ᒻ
    0.36
    ricies
    0.35
    фика
    0.35
    POSITIVE LOGITS
     export
    0.42
     ცხ
    0.37
    Mot
    0.36
     outward
    0.36
     peg
    0.35
     caminos
    0.35
     mot
    0.35
    3
    0.35
     sik
    0.34
    Pablo
    0.34
    Activations Density 0.000%

    No Known Activations