© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193085
    Prev
    Next
    INDEX
    Explanations

    bech32 addresses

    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_4_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
     to
    1.41
    et
    1.13
    ა
    1.09
    with
    1.03
    atas
    1.02
    ic
    1.01
    O
    1.00
    k
    0.99
    8
    0.99
    s
    0.96
    POSITIVE LOGITS
     in
    0.93
    го
    0.86
    もら
    0.80
    ală
    0.75
     znajdują
    0.74
    ้น
    0.73
     shavings
    0.73
    е
    0.73
    0.70
    ını
    0.70
    Activations Density 0.004%

    No Known Activations