© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 198210
    Prev
    Next
    INDEX
    Explanations

    learning rate

    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_27_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
     dielectric
    0.32
    <0xA1>
    0.31
     био
    0.30
     obeyed
    0.28
    ZnO
    0.28
     খ
    0.27
     ചരി
    0.27
    バー
    0.27
    ೖ
    0.27
    cí
    0.27
    POSITIVE LOGITS
     seconde
    0.32
    Blow
    0.32
    Luckily
    0.32
     possibilités
    0.31
    िलायंस
    0.31
     clientes
    0.30
    automne
    0.30
    hap
    0.30
     klanten
    0.30
    Hopefully
    0.30
    Activations Density 0.004%

    No Known Activations