© 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. 220131
    Prev
    Next
    INDEX
    Explanations

    both/all X and Y

    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
     Trad
    0.35
    டி
    0.35
     pend
    0.34
     económica
    0.34
    Trad
    0.33
    Moved
    0.33
    ဆင့်
    0.33
    跨
    0.33
     Prend
    0.32
     Тя
    0.32
    POSITIVE LOGITS
     бк
    0.38
     benzyl
    0.37
     മികച്ച
    0.37
    其余
    0.37
     letzten
    0.36
     دوسرا
    0.35
     परिवेश
    0.34
    崤
    0.34
    Benzyl
    0.34
     τελευτα
    0.34
    Activations Density 0.000%

    No Known Activations