© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10476
    Prev
    Next
    INDEX
    Explanations

    translate or interpret languages

    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_13_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
      
    0.26
    itzel
    0.25
    abu
    0.25
     into
    0.25
     tidur
    0.25
     hyperglycemia
    0.25
    enschaft
    0.25
    ?
    0.24
    Rosen
    0.24
    m
    0.24
    POSITIVE LOGITS
    товые
    0.30
    रि
    0.26
    㓞
    0.26
     IAEA
    0.26
    ன
    0.25
     Congolese
    0.25
    .".,
    0.25
     NIO
    0.25
    directives
    0.25
     Monet
    0.25
    Activations Density 0.045%

    No Known Activations