© 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. 101295
    Prev
    Next
    INDEX
    Explanations

    hydrogen compounds and elements

    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
    >$
    0.53
    illegal
    0.53
    ров
    0.52
    불어
    0.52
    nbsp
    0.51
    roly
    0.51
    donor
    0.50
     Alegre
    0.50
    paysys
    0.50
    dalam
    0.50
    POSITIVE LOGITS
     важно
    0.55
     ш
    0.52
     TO
    0.50
     пред
    0.50
     braiding
    0.49
     ดังนั้น
    0.48
     lids
    0.47
    нами
    0.47
     то
    0.47
    我们也
    0.46
    Activations Density 0.000%

    No Known Activations