© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90426
    Prev
    Next
    INDEX
    Explanations

    Korean, Japanese, Chinese, Russian, Dutch

    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_11_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
    ซ
    0.64
    YOU
    0.63
    CLR
    0.60
    BIT
    0.59
    ONENTS
    0.59
    𝘾
    0.59
    รี
    0.58
    ENSIONS
    0.58
    Billy
    0.57
    𝙲
    0.57
    POSITIVE LOGITS
     Те
    0.61
     Guin
    0.57
     Государ
    0.56
     behe
    0.55
     mijn
    0.54
     Mijn
    0.54
     Nature
    0.53
     ത
    0.52
    ’,
    0.52
     Trabajo
    0.52
    Activations Density 0.000%

    No Known Activations