© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257733
    Prev
    Next
    INDEX
    Explanations

    history, wars, stories, dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_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
     GPU
    0.04
    )、
    0.03
     -
    0.03
     PU
    0.03
    ，
    0.03
     adapter
    0.03
     inlet
    0.03
    、
    0.03
    ),
    0.03
    PU
    0.03
    POSITIVE LOGITS
    zeptember
    0.04
     caderno
    0.04
     cerita
    0.04
     అన్నారు
    0.03
     remarquer
    0.03
     pemer
    0.03
     agosto
    0.03
     guerras
    0.03
     நேற்று
    0.03
     historias
    0.03
    Activations Density 0.000%

    No Known Activations