© 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. 209961
    Prev
    Next
    INDEX
    Explanations

    planned implementation

    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
     óptica
    0.51
    umbles
    0.48
    ssä
    0.48
    umbing
    0.47
    tä
    0.47
    菘
    0.47
    냅
    0.46
    ulls
    0.46
    리
    0.45
    ricate
    0.45
    POSITIVE LOGITS
    γεν
    0.51
     వరు
    0.45
     czas
    0.45
     slide
    0.44
    FindAsync
    0.43
     البلد
    0.42
     ઝ
    0.41
     square
    0.41
     పార్
    0.41
     dryer
    0.41
    Activations Density 0.000%

    No Known Activations