© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87980
    Prev
    Next
    INDEX
    Explanations

    manatee and mandate

    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_3_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
    ў
    0.72
    phthal
    0.71
    ite
    0.71
     as
    0.70
     (
    0.69
     =
    0.68
    ng
    0.68
    ast
    0.65
    was
    0.65
    ns
    0.63
    POSITIVE LOGITS
    ي
    0.77
     vattati
    0.76
    anego
    0.76
    。
    0.74
    ে
    0.73
     юриди
    0.70
    ală
    0.70
    i
    0.68
     modele
    0.68
     vedit
    0.67
    Activations Density 0.001%

    No Known Activations