© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29210
    Prev
    Next
    INDEX
    Explanations

    witnessing something

    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
    te
    1.15
    ti
    1.13
    u
    1.09
    ти
    1.00
    ar
    0.96
    tiempo
    0.92
    tà
    0.91
    ся
    0.90
    tól
    0.88
    té
    0.88
    POSITIVE LOGITS
    1.14
    ید
    0.83
     }
    0.76
    瘍
    0.72
    าน
    0.71
    िक
    0.71
     সাল
    0.71
    Witness
    0.71
    ین
    0.70
    ।
    0.70
    Activations Density 0.007%

    No Known Activations