© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 207055
    Prev
    Next
    INDEX
    Explanations

    concessive conjunctions

    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
     aberrations
    0.46
     atención
    0.44
    <unused354>
    0.44
     Weierstrass
    0.43
     aberration
    0.43
     Vaish
    0.42
     atrocities
    0.41
     traite
    0.41
     blemishes
    0.41
     откло
    0.41
    POSITIVE LOGITS
    ac
    0.41
    ek
    0.41
    ak
    0.40
    akor
    0.38
    eking
    0.36
    貅
    0.35
    ent
    0.35
    cor
    0.35
    koa
    0.35
    buffered
    0.35
    Activations Density 0.000%

    No Known Activations