© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14887
    Prev
    Next
    INDEX
    Explanations

    early game

    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_13_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
    d
    0.48
    ти
    0.47
    automated
    0.47
     стали
    0.47
    重
    0.46
    n
    0.44
    форд
    0.44
    যুক্ত
    0.44
    default
    0.43
    ي
    0.43
    POSITIVE LOGITS
     fossils
    0.59
    예요
    0.57
     nœ
    0.56
     accès
    0.55
     étoile
    0.55
     procédés
    0.54
     Majorana
    0.53
     organelles
    0.53
     fries
    0.53
     chur
    0.53
    Activations Density 0.074%

    No Known Activations