© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7774
    Prev
    Next
    INDEX
    Explanations

    percentages and numbers

    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_40_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
    ົດ
    0.39
     Stream
    0.38
    ཤ
    0.38
     stream
    0.37
    Stream
    0.37
     ಸ್ಟ
    0.36
    lee
    0.35
    gado
    0.35
     வய
    0.35
    결
    0.35
    POSITIVE LOGITS
     hundred
    0.92
    一百
    0.84
     hundert
    0.84
     १००
    0.79
     száz
    0.72
     cento
    0.71
     നൂ
    0.69
     hundreds
    0.69
    hundred
    0.69
     ১৫০
    0.68
    Activations Density 0.047%

    No Known Activations