© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 101482
    Prev
    Next
    INDEX
    Explanations

    limited series, contract, confirmation, treating, forming, project, spring

    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_16_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
     vint
    0.49
     lô
    0.46
    лед
    0.46
     vét
    0.45
    rainer
    0.44
     V
    0.44
    模型
    0.43
     hel
    0.43
    v
    0.42
     postav
    0.41
    POSITIVE LOGITS
    Rate
    0.50
     сегодняш
    0.48
    auts
    0.48
    ACE
    0.47
    Topics
    0.46
    得る
    0.45
    Show
    0.45
     Telegram
    0.44
    ্যাট
    0.44
    Targets
    0.44
    Activations Density 0.000%

    No Known Activations