© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162406
    Prev
    Next
    INDEX
    Explanations

    reducing in size

    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_2_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
    1.07
    '
    1.05
    )
    1.04
     for
    1.03
     curate
    1.00
    ಂಪ
    0.98
     bustling
    0.97
     cook
    0.96
     detract
    0.94
     depolar
    0.94
    POSITIVE LOGITS
    ні
    1.55
    ק
    1.54
    ί
    1.23
    اب
    1.12
    وب
    1.06
    2
    1.05
    ە
    1.05
    ین
    1.04
    ‌هایی
    1.02
    ש
    1.02
    Activations Density 0.000%

    No Known Activations