© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232517
    Prev
    Next
    INDEX
    Explanations

    moving with speed

    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_32_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
    ዦ
    0.41
    颗
    0.40
    vore
    0.36
    र्नर
    0.36
    íč
    0.35
    िंट
    0.34
     stern
    0.34
    빨
    0.34
    搾
    0.34
     incentive
    0.33
    POSITIVE LOGITS
     Breach
    0.42
     breach
    0.41
     Pillar
    0.40
    尺寸
    0.40
     dimens
    0.39
     dt
    0.39
     hog
    0.38
    ycyj
    0.37
     Ingram
    0.37
    巾
    0.37
    Activations Density 0.003%

    No Known Activations