© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157164
    Prev
    Next
    INDEX
    Explanations

    опа, обла, or oblast

    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_2_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
    ل
    1.41
    ى
    1.33
     a
    1.22
     asegur
    1.15
    د
    1.15
     powied
    1.13
    л
    1.13
     ی
    1.12
    eros
    1.09
     заяви
    1.05
    POSITIVE LOGITS
    i
    1.42
    0
    1.30
    in
    1.22
    udsman
    1.12
    ي
    1.09
     Función
    1.09
     Version
    1.06
     Sciences
    1.05
     Defines
    1.05
     Src
    1.05
    Activations Density 0.004%

    No Known Activations