© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 60868
    Prev
    Next
    INDEX
    Explanations

    worthless or lossless

    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_59_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
    无
    2.73
    無
    2.73
     бес
    2.56
     무
    2.53
    무
    2.48
     无
    2.36
     vô
    2.28
     無
    2.22
    ไร
    2.17
    が無
    1.89
    POSITIVE LOGITS
     acutely
    0.34
    وجد
    0.34
     Vall
    0.32
    oju
    0.30
     Grit
    0.30
     जु
    0.30
     कौ
    0.30
    }_{+
    0.30
    ഭി
    0.29
    pengaruhi
    0.29
    Activations Density 0.023%

    No Known Activations