© 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. 138949
    Prev
    Next
    INDEX
    Explanations

    do verbs

    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
     well
    0.43
     swojej
    0.43
     Well
    0.42
    Well
    0.40
     తె
    0.38
     잘
    0.38
     dobrze
    0.37
     хорошо
    0.36
     swoją
    0.36
    hwnd
    0.36
    POSITIVE LOGITS
     समु
    0.38
    ःख
    0.38
     дать
    0.37
     desks
    0.37
     affili
    0.37
    竪
    0.36
    vali
    0.36
     phosphor
    0.35
    /∂
    0.35
     Desk
    0.35
    Activations Density 0.003%

    No Known Activations