© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76024
    Prev
    Next
    INDEX
    Explanations

    events scheduled for

    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_31_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
     ({
    0.33
     suspended
    0.32
    aneus
    0.30
              
    0.30
    italic
    0.30
    itens
    0.30
     allocations
    0.29
     (\
    0.29
    atakse
    0.29
    閘
    0.28
    POSITIVE LOGITS
     Несмотря
    0.34
     commandBuffer
    0.32
     Despite
    0.31
     firmness
    0.31
    Rebecca
    0.31
     Яро
    0.31
     Synth
    0.31
     improv
    0.30
     obeying
    0.30
     Remembering
    0.30
    Activations Density 0.001%

    No Known Activations