© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205279
    Prev
    Next
    INDEX
    Explanations

    K-factor explanations

    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_37_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
    ﻜ
    0.47
    𝐾
    0.41
     الك
    0.39
     bake
    0.39
    𝒌
    0.39
     KD
    0.39
     kac
    0.38
     К
    0.38
    يكا
    0.38
     १
    0.37
    POSITIVE LOGITS
     Dir
    0.43
    Dir
    0.39
    емость
    0.38
     repl
    0.37
    অম
    0.37
     dir
    0.35
     অম
    0.35
     cloned
    0.35
    ربع
    0.35
    ogenes
    0.35
    Activations Density 0.002%

    No Known Activations