© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227730
    Prev
    Next
    INDEX
    Explanations

    LH airline code, command, or hormone

    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_6_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
    ي
    1.13
    મ
    1.04
    ర
    0.98
    ர
    0.98
    י
    0.89
    ম
    0.87
    ين
    0.85
    м
    0.85
    ર
    0.85
    ש
    0.85
    POSITIVE LOGITS
    flakes
    0.72
    ።
    0.70
    IV
    0.68
    kinase
    0.68
     as
    0.67
     {
    0.67
    larını
    0.66
    numpy
    0.66
    lt
    0.64
    IOT
    0.63
    Activations Density 0.000%

    No Known Activations