© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164543
    Prev
    Next
    INDEX
    Explanations

    note this / link

    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
     presentado
    0.39
     Connor
    0.39
    p
    0.39
    競馬
    0.38
     Toronto
    0.37
     McCorm
    0.37
     Mathews
    0.37
     Bradley
    0.37
    jourd
    0.36
     Paul
    0.36
    POSITIVE LOGITS
     viti
    0.43
    \*
    0.41
    ൂരി
    0.38
     greater
    0.37
    locals
    0.37
     amide
    0.37
    =-\
    0.36
     aerosols
    0.36
     ощу
    0.36
     clots
    0.36
    Activations Density 0.013%

    No Known Activations