© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24642
    Prev
    Next
    INDEX
    Explanations

    after what

    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
    𝗴
    0.88
    𝗲
    0.80
    мы
    0.79
    geten
    0.75
    ു
    0.75
    ды
    0.73
    𝚘
    0.72
     as
    0.71
    드의
    0.70
    ехала
    0.70
    POSITIVE LOGITS
    il
    0.84
    ів
    0.73
    <0x80>
    0.64
    ين
    0.64
     integ
    0.64
    on
    0.62
     anesthet
    0.59
    ला
    0.59
     yell
    0.59
     figurative
    0.59
    Activations Density 0.001%

    No Known Activations