© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 150670
    Prev
    Next
    INDEX
    Explanations

    Note

    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_60_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
     about
    0.75
    about
    0.72
    book
    0.66
     buku
    0.60
     apie
    0.59
     tentang
    0.58
     below
    0.57
    -
    0.57
     sobre
    0.55
     کتاب
    0.55
    POSITIVE LOGITS
    e
    0.41
    was
    0.41
    ic
    0.38
     который
    0.37
     was
    0.37
    UNC
    0.36
     ic
    0.36
     який
    0.36
     Than
    0.35
    Much
    0.35
    Activations Density 0.000%

    No Known Activations