© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 200109
    Prev
    Next
    INDEX
    Explanations

    Foundation

    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
     कस
    0.39
    कस
    0.38
    ര്‍ന്ന
    0.38
    ☦
    0.38
    َل
    0.37
     intimately
    0.37
    eter
    0.36
    优雅
    0.36
    لک
    0.36
     vesc
    0.36
    POSITIVE LOGITS
     i
    0.93
     IC
    0.91
     ICI
    0.85
     IH
    0.85
     IW
    0.84
     CI
    0.82
     IA
    0.81
     IE
    0.80
     IB
    0.78
     آئی
    0.78
    Activations Density 0.001%

    No Known Activations