© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173320
    Prev
    Next
    INDEX
    Explanations

    most valuable pieces

    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
    hspace
    0.47
    height
    0.46
     With
    0.45
    with
    0.45
    Avec
    0.42
    詣
    0.41
    6
    0.41
    In
    0.41
    Durante
    0.40
    vred
    0.40
    POSITIVE LOGITS
     thicker
    0.55
     rectangle
    0.53
     rectangles
    0.49
     aata
    0.49
     mowing
    0.48
     similarities
    0.47
     gritty
    0.47
     drows
    0.47
     божомолдор
    0.47
     malleable
    0.47
    Activations Density 0.000%

    No Known Activations