© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17187
    Prev
    Next
    INDEX
    Explanations

    imgur.com links, id, defense

    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_34_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
    郯
    0.37
    żeń
    0.36
    ो
    0.35
    وب
    0.34
     шт
    0.33
    ioc
    0.32
     humid
    0.31
     BCE
    0.31
     amp
    0.30
    ō
    0.30
    POSITIVE LOGITS
    ליו
    0.36
    Daemon
    0.34
    caire
    0.34
    ATYPE
    0.33
    STRAL
    0.33
     stry
    0.33
    aitre
    0.32
     Muller
    0.31
    Ни
    0.31
    Cannon
    0.31
    Activations Density 0.038%

    No Known Activations