© 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. 14057
    Prev
    Next
    INDEX
    Explanations

    election symbol, seats, or water plan

    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
     जूनियर
    0.40
    ACLE
    0.39
    金
    0.39
     deliver
    0.37
     delivered
    0.36
    ជំន
    0.35
     Trustee
    0.35
    క్ష్
    0.35
     Junior
    0.35
     performance
    0.34
    POSITIVE LOGITS
     botanical
    0.38
     Nội
    0.38
     규
    0.37
    betrieb
    0.37
    appendix
    0.36
    SEQU
    0.36
     botany
    0.35
     జరిగ
    0.35
    requestCode
    0.35
    ագր
    0.35
    Activations Density 0.007%

    No Known Activations