© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34630
    Prev
    Next
    INDEX
    Explanations

    visual prompts for AI images

    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_31_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
    涕
    0.27
    etimes
    0.25
    配布
    0.25
     nausea
    0.24
    霾
    0.24
    㖡
    0.24
    heden
    0.24
     ನಡೆಸ
    0.24
    罄
    0.24
     발행
    0.23
    POSITIVE LOGITS
     hierarch
    0.25
    ph
    0.24
     comando
    0.24
     perfil
    0.24
     unresolved
    0.24
     razon
    0.23
    コマンド
    0.23
     Voltage
    0.23
    Resolved
    0.23
    questao
    0.23
    Activations Density 0.004%

    No Known Activations