© 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. 155517
    Prev
    Next
    INDEX
    Explanations

    C++ programming code

    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
     >>
    2.25
     <<
    2.20
    >>
    2.17
    <<
    2.06
     >>>
    1.75
    )<<
    1.66
    >>>
    1.63
    >>,
    1.60
     "<<
    1.59
    "<<
    1.57
    POSITIVE LOGITS
    impulan
    0.37
    โจ
    0.36
     invariably
    0.35
    mtr
    0.35
     motions
    0.34
     perdre
    0.34
    xxxxx
    0.34
     entitlements
    0.34
     آهي
    0.34
    chalk
    0.33
    Activations Density 0.003%

    No Known Activations