© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167426
    Prev
    Next
    INDEX
    Explanations

    can/could you

    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_31_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
     يمكنك
    0.35
     applies
    0.34
     الحالي
    0.32
    ष्कार
    0.32
    🍅
    0.32
     الشي
    0.32
     можли
    0.31
    Possible
    0.31
    Sole
    0.31
    ዎችን
    0.31
    POSITIVE LOGITS
     standardised
    0.36
    renderSquare
    0.35
    謹
    0.34
     perp
    0.33
    보다는
    0.33
    雦
    0.33
     szczególnie
    0.32
     TestBed
    0.31
     갤럭시
    0.31
     justiça
    0.31
    Activations Density 0.004%

    No Known Activations