© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25781
    Prev
    Next
    INDEX
    Explanations

    Fifth Generation, Avenue, Fifth Disease

    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_10_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
    يف
    0.77
     indemnify
    0.72
     idempotent
    0.71
     يعد
    0.69
     idealized
    0.68
     bioc
    0.66
     idempot
    0.66
    用
    0.66
     delimit
    0.65
     excell
    0.65
    POSITIVE LOGITS
    to
    1.10
    ación
    0.86
    ۰
    0.84
    is
    0.78
    are
    0.76
    and
    0.75
    ری
    0.75
    с
    0.75
    fourth
    0.74
    に
    0.73
    Activations Density 0.011%

    No Known Activations