© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1545
    Prev
    Next
    INDEX
    Explanations

    begins with h

    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
     завое
    0.44
    ಶಸ್
    0.37
     पैर
    0.37
    కాలు
    0.36
    GoString
    0.35
    ibranch
    0.35
     разговари
    0.35
    𒄀
    0.34
    nykh
    0.34
     berjumpa
    0.34
    POSITIVE LOGITS
     halt
    0.48
     Höhen
    0.45
     halts
    0.44
     H
    0.44
     Heaven
    0.44
     ہ
    0.43
     heaps
    0.43
     halted
    0.41
     hå
    0.41
     histories
    0.40
    Activations Density 0.030%

    No Known Activations