© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 98036
    Prev
    Next
    INDEX
    Explanations

    belly baking, stomach twisted

    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_14_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
     torso
    0.60
     cintura
    0.57
     бк
    0.56
     tummy
    0.53
    肚
    0.53
     Cyst
    0.51
     abdom
    0.49
     estómago
    0.49
     abdominal
    0.49
     Spinal
    0.49
    POSITIVE LOGITS
    čių
    0.60
    Tov
    0.53
    Mar
    0.51
    ArrayList
    0.49
    दारा
    0.48
    թ
    0.48
     চোখ
    0.48
    ট্র
    0.48
    ڄ
    0.48
    ական
    0.47
    Activations Density 0.006%

    No Known Activations