© 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. 27972
    Prev
    Next
    INDEX
    Explanations

    FOR IMMEDIATE RELEASE

    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
     to
    0.71
     as
    0.66
    lık
    0.62
     a
    0.61
     scores
    0.59
    ishes
    0.58
    תר
    0.57
    </b>
    0.57
     indicator
    0.55
     premios
    0.55
    POSITIVE LOGITS
    W
    0.73
    及ひ
    0.71
    0
    0.70
    他和
    0.69
    5
    0.68
    uning
    0.68
    7
    0.68
    朳
    0.68
    вающей
    0.67
    4
    0.67
    Activations Density 0.002%

    No Known Activations