© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164988
    Prev
    Next
    INDEX
    Explanations

    homicides

    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_13_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
     collation
    0.27
     ఒకటి
    0.26
    RAchievement
    0.26
     rainbow
    0.26
     صن
    0.26
     nutrients
    0.25
    纖
    0.25
     mosaics
    0.25
     rainbows
    0.25
    𝟮
    0.24
    POSITIVE LOGITS
     Seigneur
    0.33
     Arms
    0.30
     Sentence
    0.28
     Sinha
    0.27
     निराश
    0.27
     had
    0.27
     Zaman
    0.27
    okane
    0.27
     خیال
    0.26
     Koval
    0.26
    Activations Density 0.001%

    No Known Activations