© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 198906
    Prev
    Next
    INDEX
    Explanations

    image feature detection

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     HSP
    0.42
     HIF
    0.38
     Or
    0.38
     Basic
    0.38
     basic
    0.38
    興趣
    0.37
     Non
    0.37
     R
    0.36
     Forster
    0.36
     McColl
    0.36
    POSITIVE LOGITS
    vre
    0.43
     कट
    0.38
    க்கூ
    0.37
    marginLeft
    0.35
    ecycle
    0.35
     عمد
    0.35
    nese
    0.34
     esper
    0.34
     کامی
    0.34
    挂
    0.34
    Activations Density 0.001%

    No Known Activations