© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 96840
    Prev
    Next
    INDEX
    Explanations

    prompt engineering

    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_14_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
    at
    0.70
    a
    0.66
    as
    0.65
     l
    0.62
     then
    0.62
    ırma
    0.57
     tedes
    0.57
     scuola
    0.55
    s
    0.54
     soldi
    0.53
    POSITIVE LOGITS
    gateTime
    0.57
    ックス
    0.54
    JMenuItem
    0.54
    োজন
    0.53
    ForItem
    0.53
     イタリア
    0.53
     О
    0.52
     Ор
    0.51
    Wrist
    0.51
    Leicester
    0.51
    Activations Density 0.004%

    No Known Activations