© 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. 249597
    Prev
    Next
    INDEX
    Explanations

    ends in "ff"

    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
    Tip
    0.34
     புற
    0.34
    Stock
    0.34
     dies
    0.33
    ስተ
    0.33
    stock
    0.32
     consisting
    0.32
     앞
    0.32
    ppets
    0.32
    gg
    0.32
    POSITIVE LOGITS
     EFF
    0.56
    EFF
    0.54
     Muff
    0.53
     eff
    0.51
    bff
    0.51
     Duff
    0.51
    Huff
    0.51
     BAFF
    0.50
    uff
    0.49
     Goff
    0.49
    Activations Density 0.000%

    No Known Activations