© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170596
    Prev
    Next
    INDEX
    Explanations

    Witt

    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_56_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
     Spl
    0.45
     Poj
    0.41
    ண்டி
    0.39
     Kimura
    0.37
    Spl
    0.37
     Favorites
    0.37
    晋
    0.37
    晉
    0.36
     Lucky
    0.36
     Volume
    0.35
    POSITIVE LOGITS
    ນ
    0.43
    orne
    0.43
    ज्ञानिक
    0.38
    ackBar
    0.38
    ورہ
    0.38
     pending
    0.37
    ørn
    0.37
    ){//
    0.37
     നാല
    0.37
    veg
    0.36
    Activations Density 0.000%

    No Known Activations