© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46573
    Prev
    Next
    INDEX
    Explanations

    capital adequacy ratios

    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_3_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
    </h3>
    0.70
     polynomials
    0.62
    ס
    0.61
     IMPORT
    0.61
    ียว
    0.61
    t
    0.61
     encontró
    0.60
     ambito
    0.60
    ியை
    0.60
     intégr
    0.60
    POSITIVE LOGITS
    か
    0.60
    per
    0.59
    ro
    0.59
    ged
    0.58
    ca
    0.58
    gi
    0.57
    me
    0.57
    gunakan
    0.56
    ണ
    0.56
    du
    0.56
    Activations Density 0.002%

    No Known Activations