© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90932
    Prev
    Next
    INDEX
    Explanations

    in respect of

    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_11_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
    昅
    0.67
    䄪
    0.67
    圤
    0.66
     Atth
    0.63
     വര
    0.63
    𝒐
    0.63
    𝒊
    0.62
     தன்னை
    0.61
    徃
    0.60
    溆
    0.60
    POSITIVE LOGITS
    s
    0.81
    2
    0.71
    ↵
    0.68
    ς
    0.66
     vocal
    0.64
    ים
    0.64
    ों
    0.64
    èvre
    0.63
     are
    0.62
     voc
    0.61
    Activations Density 0.000%

    No Known Activations