© 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. 196007
    Prev
    Next
    INDEX
    Explanations

    symbols

    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
     tetap
    0.39
     తీ
    0.38
    ove
    0.38
    दू
    0.38
     월
    0.38
     రాజు
    0.37
    istaa
    0.36
     исти
    0.36
     بہتر
    0.36
    रहे
    0.36
    POSITIVE LOGITS
    தம்ப
    0.37
     برم
    0.37
    કોટ
    0.35
    ;<
    0.35
     ToolsVersion
    0.35
    됨
    0.34
    ستی
    0.34
     richtigen
    0.34
     চুপ
    0.34
    Rightarrow
    0.34
    Activations Density 0.005%

    No Known Activations