© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 102203
    Prev
    Next
    INDEX
    Explanations

    human evaluation

    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_16_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
    ૂ
    0.38
    ically
    0.37
    utim
    0.36
    im
    0.36
     understand
    0.36
     verstehen
    0.36
     μου
    0.35
    phyr
    0.35
    utscher
    0.35
    hesize
    0.35
    POSITIVE LOGITS
     Workers
    0.46
    🏭
    0.44
    Workers
    0.44
     Pandas
    0.42
     Вайлдберриз
    0.42
    错误
    0.42
    workers
    0.41
    函数的
    0.41
    足够的
    0.41
    传奇
    0.41
    Activations Density 0.035%

    No Known Activations