© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206241
    Prev
    Next
    INDEX
    Explanations

    rotation and spinning

    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_20_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
     feeble
    0.43
     എടു
    0.43
     लिखा
    0.42
     எடுக்க
    0.41
     энерги
    0.41
     पेड़
    0.40
     deeds
    0.40
    /</
    0.40
     peanuts
    0.40
     пла
    0.40
    POSITIVE LOGITS
    ष्टमी
    0.57
    Manufacturer
    0.50
    나는
    0.45
    Medical
    0.43
    skiej
    0.43
    š
    0.43
    lije
    0.42
    엘
    0.42
     colaboración
    0.41
     cooperación
    0.41
    Activations Density 0.001%

    No Known Activations