© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176575
    Prev
    Next
    INDEX
    Explanations

    half of

    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_24_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
    te
    0.58
    та
    0.57
    ем
    0.54
    й
    0.51
    -
    0.50
    ка
    0.50
    ↵
    0.49
    les
    0.48
    ة
    0.48
    те
    0.48
    POSITIVE LOGITS
     政府
    0.49
    ँसी
    0.48
     কাগজে
    0.47
     VMs
    0.46
    Ꮀ
    0.44
    র্কের
    0.43
     Bronco
    0.42
     καθ
    0.42
    কারীরা
    0.41
    क्शंस
    0.41
    Activations Density 0.000%

    No Known Activations