© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 216078
    Prev
    Next
    INDEX
    Explanations

    Ele

    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_50_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
    ++',
    0.42
    ői
    0.40
    ंतिक
    0.40
    +}$,
    0.40
     sekar
    0.39
    wParam
    0.39
    ної
    0.38
     Perak
    0.38
    жени
    0.37
    nae
    0.37
    POSITIVE LOGITS
    IS
    0.41
    otes
    0.41
    isent
    0.40
    MAK
    0.39
    雔
    0.39
    BL
    0.38
     angulis
    0.38
    מק
    0.38
    BID
    0.37
    igis
    0.37
    Activations Density 0.000%

    No Known Activations