© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198979
    Prev
    Next
    INDEX
    Explanations

    initial capital letters and numbers or IPA

    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_15_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
    R
    0.59
    agro
    0.57
    J
    0.57
    ään
    0.54
    S
    0.54
    Si
    0.54
    baar
    0.53
    Cl
    0.53
    াজার
    0.53
    아
    0.53
    POSITIVE LOGITS
     thuyết
    0.51
     buddhav
    0.50
     isotherms
    0.49
     adhipp
    0.48
     suficiente
    0.48
     perj
    0.47
     sufficient
    0.46
     ditth
    0.46
     Dalai
    0.46
     convolutions
    0.46
    Activations Density 0.000%

    No Known Activations