© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64516
    Prev
    Next
    INDEX
    Explanations

    beaches

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    Salt
    0.43
    塩
    0.39
     scrollBody
    0.38
    床
    0.37
    锈
    0.37
    桔
    0.37
    ग्री
    0.36
    Blue
    0.36
     internalType
    0.36
     Salt
    0.36
    POSITIVE LOGITS
     flag
    0.46
    旗
    0.46
     Flag
    0.43
     amerikanischen
    0.42
     American
    0.39
     американ
    0.39
     bathing
    0.38
     पवार
    0.38
    IPP
    0.38
     Dutch
    0.38
    Activations Density 0.002%

    No Known Activations