© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 151322
    Prev
    Next
    INDEX
    Explanations

    it working

    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_59_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
     Be
    0.52
    Be
    0.48
    be
    0.47
     im
    0.43
    itm
    0.41
    has
    0.40
    was
    0.38
    ']==
    0.38
     was
    0.37
    plc
    0.37
    POSITIVE LOGITS
     store
    0.71
     Store
    0.68
     STORE
    0.59
    Store
    0.59
     shoot
    0.57
     state
    0.51
     મારી
    0.50
     دولة
    0.50
     download
    0.50
     स्टोर
    0.49
    Activations Density 0.002%

    No Known Activations