© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37242
    Prev
    Next
    INDEX
    Explanations

    diverse symbols

    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
     Ch
    0.72
     ch
    0.63
    Ch
    0.53
     CH
    0.52
     Ч
    0.49
     च
    0.47
     ys
    0.43
     Chit
    0.42
     Ac
    0.42
    YX
    0.42
    POSITIVE LOGITS
    鲷
    0.39
    ジオ
    0.37
     लाहि
    0.37
    摷
    0.35
    ioi
    0.34
    ਊ
    0.34
    itettura
    0.34
    Dio
    0.33
    .°
    0.33
    巨
    0.32
    Activations Density 0.033%

    No Known Activations