© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260822
    Prev
    Next
    INDEX
    Explanations

    createCanvas or size

    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_22_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
     KAHN
    0.44
    otá
    0.42
    winged
    0.42
    ज्ञ
    0.42
    ದೆ
    0.42
     legger
    0.42
    厷
    0.42
    ़
    0.42
    蹌
    0.41
    ámenes
    0.41
    POSITIVE LOGITS
    నాలు
    0.41
     ట
    0.40
    ابقات
    0.39
     চালান
    0.38
     sensitivity
    0.38
     Decentral
    0.38
     decentralized
    0.38
    ensitive
    0.37
     Sensitivity
    0.37
    ట
    0.37
    Activations Density 0.000%

    No Known Activations