© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 164642
    Prev
    Next
    INDEX
    Explanations

    frame and padding modifiers

    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
     Text
    0.42
    ках
    0.39
     namespaces
    0.39
     φα
    0.39
    纹
    0.38
    kloud
    0.37
    ｯ
    0.37
    泊
    0.36
     至
    0.35
     Pru
    0.35
    POSITIVE LOGITS
    Virginia
    0.43
     auprès
    0.42
    oncesto
    0.41
     virginia
    0.40
    manirrahim
    0.39
     диа
    0.38
     Virginia
    0.37
     Владимира
    0.37
    ικής
    0.36
    ৃষ্ট
    0.36
    Activations Density 0.000%

    No Known Activations