© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44123
    Prev
    Next
    INDEX
    Explanations

    ssti or st followed by punctuation or lab/analysis

    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_3_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
    ни
    0.83
    ي
    0.79
    ారు
    0.70
    ğin
    0.70
    логи
    0.70
    وي
    0.69
    C
    0.68
    becue
    0.68
    كمة
    0.68
    、
    0.68
    POSITIVE LOGITS
    u
    1.03
    the
    0.79
     an
    0.74
     یا
    0.70
    {
    0.69
     dinn
    0.69
    ลำ
    0.65
     sensit
    0.64
     billionaires
    0.61
     molar
    0.61
    Activations Density 0.007%

    No Known Activations