© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5254
    Prev
    Next
    INDEX
    Explanations

    ask for information

    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_40_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
    besides
    0.40
    ới
    0.39
     artistes
    0.39
    Ớ
    0.39
     besides
    0.39
    ळं
    0.39
    wherein
    0.38
     artiste
    0.38
    ья
    0.37
     ვა
    0.37
    POSITIVE LOGITS
     desenhos
    0.39
     cous
    0.38
     personali
    0.38
    ⛰
    0.38
     maps
    0.35
    😶
    0.35
    😵
    0.35
    🌛
    0.34
     روم
    0.34
    する方法
    0.34
    Activations Density 0.030%

    No Known Activations