© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35518
    Prev
    Next
    INDEX
    Explanations

    talking or discussing abstract concepts

    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_31_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
     irão
    0.43
    Ring
    0.38
    laan
    0.38
    cri
    0.38
     ดังนั้น
    0.38
    Respond
    0.37
     નોંધ
    0.37
    睞
    0.36
    ర్థ
    0.36
    Latency
    0.36
    POSITIVE LOGITS
     talk
    0.58
     Talk
    0.43
    talk
    0.43
    谈
    0.39
    кот
    0.39
     talks
    0.38
     govor
    0.38
     konuş
    0.38
     talked
    0.38
    Talk
    0.37
    Activations Density 0.041%

    No Known Activations