© 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. 194665
    Prev
    Next
    INDEX
    Explanations

    move

    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
     herd
    0.20
     s
    0.20
     ru
    0.20
     weet
    0.20
     Sight
    0.20
     gunfire
    0.19
     scen
    0.18
     зад
    0.18
     Highlands
    0.18
     p
    0.18
    POSITIVE LOGITS
    सबुक
    0.22
    apayati
    0.22
    oucault
    0.21
    الب
    0.20
    vegetarian
    0.20
    Consulta
    0.20
    Vas
    0.20
     новое
    0.20
    avacanam
    0.20
    umlu
    0.20
    Activations Density 0.013%

    No Known Activations