© 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. 26045
    Prev
    Next
    INDEX
    Explanations

    inevitable outcomes

    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
     It
    0.95
     father
    0.70
     nauk
    0.69
     superpower
    0.68
     fertilizer
    0.68
    ח
    0.66
    )،
    0.66
     This
    0.65
     hunger
    0.64
     '/',
    0.64
    POSITIVE LOGITS
    وري
    0.79
    šky
    0.78
    tries
    0.75
    ení
    0.73
    ested
    0.71
    omes
    0.70
    t
    0.70
    更换
    0.69
    ření
    0.68
    有意
    0.68
    Activations Density 0.002%

    No Known Activations