© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246637
    Prev
    Next
    INDEX
    Explanations

    disagree

    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_40_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
     slightly
    0.40
     श्रे
    0.39
     légèrement
    0.35
     oppose
    0.35
    ᴥ
    0.34
    pecia
    0.34
     pain
    0.33
     trochę
    0.33
    Ellen
    0.32
     rye
    0.32
    POSITIVE LOGITS
     BIL
    0.41
     Bila
    0.38
     समझ
    0.38
     söyled
    0.37
    եկ
    0.37
     বুঝতে
    0.37
    㳻
    0.36
    ibili
    0.36
     পুল
    0.36
     océ
    0.36
    Activations Density 0.002%

    No Known Activations