© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13602
    Prev
    Next
    INDEX
    Explanations

    RA, Alpha, Alfa, α

    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_40_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
     kup
    0.44
     laguna
    0.40
     Lagrange
    0.40
     Kauff
    0.39
    黑
    0.39
     Laguna
    0.38
    orty
    0.38
     Brentwood
    0.38
     Preventive
    0.37
    ademia
    0.36
    POSITIVE LOGITS
     RA
    0.79
     alpha
    0.74
    alpha
    0.73
    Alpha
    0.68
     Alpha
    0.65
     α
    0.64
    α
    0.62
    RA
    0.61
     Ra
    0.61
     alfa
    0.58
    Activations Density 0.026%

    No Known Activations