© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16191
    Prev
    Next
    INDEX
    Explanations

    https:// URLs

    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
    жан
    0.42
    нер
    0.37
    कून
    0.37
    ERS
    0.37
    rocks
    0.36
    Claudia
    0.36
    heure
    0.36
    𝔦
    0.35
    ക്കൊ
    0.35
     ভগ
    0.35
    POSITIVE LOGITS
     targets
    0.41
     बारह
    0.41
     target
    0.41
     sik
    0.40
     continuity
    0.40
     radiated
    0.39
     cellules
    0.38
     消
    0.37
    sik
    0.36
     세포
    0.36
    Activations Density 0.011%

    No Known Activations