© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 131938
    Prev
    Next
    INDEX
    Explanations

    LTD|LTP|LCY

    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_6_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
    و
    1.49
    as
    1.13
    u
    1.09
    ו
    0.96
    ar
    0.94
    a
    0.89
    an
    0.84
    on
    0.81
    er
    0.78
    o
    0.78
    POSITIVE LOGITS
     was
    0.63
     It
    0.62
    来て
    0.59
     pessoal
    0.58
     I
    0.57
    ự
    0.55
     hóa
    0.55
    ﺀ
    0.55
    рия
    0.54
    IEN
    0.54
    Activations Density 0.001%

    No Known Activations