© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45786
    Prev
    Next
    INDEX
    Explanations

    content creation

    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_10_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
     memperhatikan
    0.24
     tangible
    0.23
     Angebot
    0.22
     גדול
    0.22
     embora
    0.22
     Darstellung
    0.22
     գ
    0.22
     dimensionality
    0.22
     SHOULD
    0.22
     მთ
    0.22
    POSITIVE LOGITS
    و
    0.34
    م
    0.34
    m
    0.33
    이
    0.32
    u
    0.31
    y
    0.30
    ल
    0.28
    й
    0.28
    л
    0.28
    i
    0.27
    Activations Density 0.011%

    No Known Activations