© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12926
    Prev
    Next
    INDEX
    Explanations

    download website hosting

    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_13_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
     l
    0.40
     Landmark
    0.38
    {
    0.38
    https
    0.37
    It
    0.37
     But
    0.37
    宁波
    0.36
    Also
    0.36
    FP
    0.36
    What
    0.35
    POSITIVE LOGITS
     iguais
    0.48
     mãe
    0.44
     ඇත
    0.44
     mỗi
    0.42
     véh
    0.42
     abaixo
    0.42
    膾
    0.41
     basil
    0.40
     maneira
    0.40
    堬
    0.39
    Activations Density 0.281%

    No Known Activations