© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 81243
    Prev
    Next
    INDEX
    Explanations

    specific foreign terms

    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_53_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
     ه
    0.46
     horizontal
    0.41
    MethodBeat
    0.40
    Horizontal
    0.40
    umption
    0.39
     Horizontal
    0.39
    ห
    0.39
    horizontal
    0.38
    hi
    0.37
     Barn
    0.37
    POSITIVE LOGITS
     ros
    0.48
     ek
    0.47
     Incl
    0.42
    蜴
    0.39
    र्सेज
    0.38
     кон
    0.38
     EK
    0.37
     inn
    0.37
     Εκ
    0.37
     trội
    0.37
    Activations Density 0.002%

    No Known Activations