© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141918
    Prev
    Next
    INDEX
    Explanations

    rafting and paintball

    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_12_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
     የሚያ
    0.57
    ARN
    0.55
     मोन
    0.52
    酘
    0.52
    hkar
    0.51
    Fashion
    0.50
    racción
    0.50
     Kardashian
    0.50
    жли
    0.50
     sumptuous
    0.50
    POSITIVE LOGITS
    <0x80>
    0.54
     canisters
    0.53
     konto
    0.51
     ibis
    0.49
     out
    0.48
     convers
    0.48
     inform
    0.48
     komple
    0.48
     knives
    0.48
    u
    0.47
    Activations Density 0.001%

    No Known Activations