© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89525
    Prev
    Next
    INDEX
    Explanations

    drone strike

    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_3_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
    s
    0.84
    ため
    0.70
    l
    0.70
    har
    0.68
    lal
    0.68
    lang
    0.67
    IL
    0.66
    لو
    0.66
    lle
    0.65
    lag
    0.64
    POSITIVE LOGITS
    ="
    0.73
    TimeDict
    0.73
    ८
    0.73
    ),
    0.68
    ку
    0.68
    ्ड
    0.67
    ),(
    0.67
    છી
    0.66
    ‌هایی
    0.66
    otipi
    0.66
    Activations Density 0.000%

    No Known Activations