© 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. 232633
    Prev
    Next
    INDEX
    Explanations

    `.

    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
     muchas
    0.42
     many
    0.39
    islava
    0.38
     algunas
    0.38
    윌
    0.37
    âte
    0.37
    tailed
    0.37
    滙
    0.37
     Rojas
    0.36
     많은
    0.36
    POSITIVE LOGITS
    Every
    0.51
     Every
    0.44
    every
    0.44
     renou
    0.40
     every
    0.40
     Death
    0.39
     dxe
    0.39
     jis
    0.37
    vous
    0.37
    forever
    0.37
    Activations Density 0.026%

    No Known Activations