© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43726
    Prev
    Next
    INDEX
    Explanations

    default camera

    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_22_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
     outside
    0.41
    outside
    0.40
    equipped
    0.39
     specialising
    0.38
     imitating
    0.38
    fortunately
    0.37
    !=
    0.37
    adecimal
    0.37
    Lucida
    0.36
    🍇
    0.36
    POSITIVE LOGITS
     Injury
    0.37
    рку
    0.36
     Question
    0.36
     história
    0.35
     обзор
    0.35
     desafios
    0.34
     lahan
    0.34
     Shah
    0.33
    Question
    0.33
     истории
    0.33
    Activations Density 0.000%

    No Known Activations