© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 5117
    Prev
    Next
    INDEX
    Explanations

    book condition and damage

    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_38_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
     finals
    0.41
     matin
    0.41
    overview
    0.37
    冒险
    0.37
     particle
    0.37
     alttext
    0.36
    midnight
    0.36
     靴
    0.36
     अंदर
    0.36
     invoc
    0.36
    POSITIVE LOGITS
     earthquake
    0.45
     Earthquake
    0.44
    裂
    0.43
     cracked
    0.43
     rupture
    0.43
     cracks
    0.43
     esquina
    0.43
     terrem
    0.43
     Fracture
    0.42
    Kang
    0.41
    Activations Density 0.002%

    No Known Activations