© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105375
    Prev
    Next
    INDEX
    Explanations

    "Double-Edged Sword"

    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_1_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
    ↵
    0.70
    je
    0.69
    ite
    0.68
    mph
    0.67
    fe
    0.66
    ali
    0.63
    foot
    0.63
    ます
    0.61
    iy
    0.61
    ji
    0.61
    POSITIVE LOGITS
    ED
    1.06
    u
    1.02
    ER
    1.01
    দ
    0.97
    ur
    0.94
    ي
    0.93
    ES
    0.92
     alguno
    0.92
    ক
    0.91
    UEL
    0.91
    Activations Density 0.000%

    No Known Activations