© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 122797
    Prev
    Next
    INDEX
    Explanations

    miraculous, mirabilandia, mirvac

    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_37_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
    φέρον
    0.43
    ශ්‍ය
    0.38
    鎗
    0.38
     impurity
    0.38
    פות
    0.36
    蒈
    0.36
     currents
    0.35
    袍
    0.35
     тер
    0.35
     Currents
    0.34
    POSITIVE LOGITS
     means
    0.40
     GPA
    0.38
    urndata
    0.38
    登
    0.37
     mor
    0.37
     ничек
    0.37
    ီ
    0.36
    ich
    0.36
    Means
    0.36
    镭
    0.36
    Activations Density 0.001%

    No Known Activations