© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 221747
    Prev
    Next
    INDEX
    Explanations

    Guild Award, oci terra

    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_10_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
    :
    0.58
    م
    0.57
    en
    0.57
    es
    0.56
    un
    0.54
     literate
    0.53
    ம்
    0.52
     metaphorical
    0.52
    ation
    0.51
    är
    0.50
    POSITIVE LOGITS
    to
    0.60
     ImageIcon
    0.58
     Termin
    0.57
     ಸ್ಥಳ
    0.57
     Configur
    0.56
     Transform
    0.55
     Structure
    0.55
    })
    0.54
     Proced
    0.54
    它可以
    0.54
    Activations Density 0.001%

    No Known Activations