© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38697
    Prev
    Next
    INDEX
    Explanations

    0

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    या
    0.37
    ଯ
    0.35
     मथुरा
    0.34
    𝖾
    0.34
    টা
    0.33
     zosta
    0.32
     Palaiseau
    0.32
    યા
    0.32
     запро
    0.32
     παρά
    0.32
    POSITIVE LOGITS
    ຜະລິດຕ
    0.38
    ográfico
    0.37
     कनेक्टिव
    0.35
    ‹
    0.34
    也不知道
    0.34
     NSA
    0.33
    éricos
    0.33
    killers
    0.33
    .""
    0.32
    ্ল
    0.31
    Activations Density 0.022%

    No Known Activations