© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 458
    Prev
    Next
    INDEX
    Explanations

    body language, inflation, horror

    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_40_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
    zadeh
    0.34
    ꜜ
    0.33
     Tsing
    0.33
    ྩ
    0.32
     सै
    0.31
     rayons
    0.30
    sterling
    0.30
    ᾖ
    0.30
     उठाए
    0.30
    ugar
    0.29
    POSITIVE LOGITS
     body
    1.80
     Body
    1.63
    body
    1.54
     बॉडी
    1.50
     BODY
    1.50
    Body
    1.49
    BODY
    1.32
    ボディ
    1.31
     lichaam
    1.26
     cuerpo
    1.20
    Activations Density 0.095%

    No Known Activations