© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246247
    Prev
    Next
    INDEX
    Explanations

    `bi` related tokens

    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_40_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
    䉿
    0.40
    MacroExpansion
    0.38
    Comm
    0.38
    Boston
    0.38
    boolean
    0.37
    Expanded
    0.37
    ځ
    0.36
    䉍
    0.36
    ܙ
    0.36
    expanded
    0.36
    POSITIVE LOGITS
     Thinking
    0.40
     thinking
    0.40
    hā
    0.38
     advices
    0.37
     conserv
    0.36
    iani
    0.36
     బ్యాం
    0.36
    ärke
    0.35
    смо
    0.35
     смо
    0.35
    Activations Density 0.000%

    No Known Activations