© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2395
    Prev
    Next
    INDEX
    Explanations

    Regional Disparities

    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_39_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
    躹
    0.51
    𒊏
    0.48
    ណ៌
    0.48
    ᱖
    0.48
    呠
    0.48
     باتوں
    0.47
     Crore
    0.47
    িত্যক্ত
    0.46
    ㄛ
    0.46
    月に
    0.45
    POSITIVE LOGITS
     실
    0.74
     공
    0.71
     매
    0.65
     연
    0.64
     관련
    0.64
     베
    0.62
     생
    0.62
    에
    0.61
     대
    0.61
     가
    0.61
    Activations Density 0.015%

    No Known Activations