© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87260
    Prev
    Next
    INDEX
    Explanations

    Kandinsky

    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_3_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
    r
    0.62
    stufe
    0.61
    Were
    0.61
    e
    0.58
     двох
    0.57
    o
    0.55
    an
    0.55
    although
    0.55
    aniline
    0.54
    nove
    0.54
    POSITIVE LOGITS
     to
    0.94
    یت
    0.93
     are
    0.86
    у
    0.80
    ری
    0.79
     It
    0.78
     of
    0.76
     smiles
    0.76
    يل
    0.76
    یس
    0.75
    Activations Density 0.000%

    No Known Activations