© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 222361
    Prev
    Next
    INDEX
    Explanations

    aspirational equivalents

    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
     proiect
    0.54
     colore
    0.52
    .$,
    0.51
     publicar
    0.51
     couleur
    0.51
    ωσε
    0.50
     ambito
    0.50
     berwarna
    0.50
    域
    0.49
     diámetro
    0.49
    POSITIVE LOGITS
    iala
    0.54
    icing
    0.52
    ise
    0.49
    ulk
    0.49
    oying
    0.48
    ny
    0.47
    uster
    0.47
    rb
    0.45
    kun
    0.45
    `
    0.45
    Activations Density 0.000%

    No Known Activations