© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 166983
    Prev
    Next
    INDEX
    Explanations

    7 3

    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_34_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
     않는
    0.36
     unbelievable
    0.35
     Farley
    0.35
     FAR
    0.34
    写
    0.34
     தெளிவாக
    0.34
     செய்யவும்
    0.34
     Marquis
    0.34
    หวาน
    0.34
    边
    0.34
    POSITIVE LOGITS
    itaria
    0.40
     lecteurs
    0.39
    নেল
    0.39
    ifle
    0.38
     lectores
    0.38
     revêt
    0.36
    بي
    0.35
     momentos
    0.35
     involuc
    0.35
     التص
    0.34
    Activations Density 0.001%

    No Known Activations