© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18292
    Prev
    Next
    INDEX
    Explanations

    #

    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_15_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
     bác
    0.23
     vudd
    0.23
     ساعات
    0.22
     нейтро
    0.21
     terlalu
    0.21
     vadati
    0.21
     enseignants
    0.21
    ე
    0.21
     spalle
    0.20
     mondiale
    0.19
    POSITIVE LOGITS
     is
    0.26
    ford
    0.26
    respon
    0.25
    mobility
    0.25
    reden
    0.24
    mel
    0.24
    ps
    0.24
    prov
    0.24
    son
    0.24
    umper
    0.23
    Activations Density 0.009%

    No Known Activations