© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 206668
    Prev
    Next
    INDEX
    Explanations

    they performing actions

    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_25_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
     flexion
    0.47
    桎
    0.42
     inoculum
    0.41
    regnum
    0.41
     gonflement
    0.40
     fucked
    0.39
     ماضی
    0.39
     раск
    0.38
     vart
    0.38
    乸
    0.38
    POSITIVE LOGITS
     obtained
    0.43
     others
    0.41
    itä
    0.39
     Smith
    0.38
    osa
    0.37
     तेरी
    0.37
    erna
    0.36
    atche
    0.36
     Smo
    0.36
    ana
    0.35
    Activations Density 0.003%

    No Known Activations