© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172347
    Prev
    Next
    INDEX
    Explanations

    lower body parts

    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
     inland
    0.24
    tableName
    0.23
     통해
    0.23
     bunnies
    0.22
     overridden
    0.22
    상을
    0.22
    عت
    0.22
    )}+
    0.21
    পুরে
    0.21
     کۆ
    0.21
    POSITIVE LOGITS
     movimento
    0.29
    variable
    0.28
     সমস্যাবলী
    0.26
     mistura
    0.26
     tecnologia
    0.25
     variáveis
    0.25
     dessin
    0.25
    事的
    0.24
     сильно
    0.24
     असंभव
    0.24
    Activations Density 0.002%

    No Known Activations