© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210657
    Prev
    Next
    INDEX
    Explanations

    essential, important, good

    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_20_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
    ocrine
    0.22
    products
    0.21
    organized
    0.21
    ocyclic
    0.21
    濯
    0.21
    fact
    0.21
    প্রণ
    0.21
    organised
    0.21
     prodotto
    0.20
    educt
    0.20
    POSITIVE LOGITS
     grit
    0.23
     k
    0.20
     symbols
    0.19
     vestiges
    0.19
     pique
    0.19
     ew
    0.18
     question
    0.18
     अ
    0.18
     क
    0.18
     aforementioned
    0.18
    Activations Density 0.000%

    No Known Activations