© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46056
    Prev
    Next
    INDEX
    Explanations

    interpolate, vuelto viral

    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_10_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
     equivale
    0.58
     taraf
    0.58
     telephone
    0.57
     originalmente
    0.57
     constru
    0.56
     malah
    0.55
     satu
    0.55
    マ
    0.55
     equipo
    0.55
     efectuar
    0.55
    POSITIVE LOGITS
     Intellectual
    0.55
     Tires
    0.50
    checking
    0.49
     Checking
    0.48
    details
    0.48
     Manual
    0.48
     Spending
    0.48
    weights
    0.47
    there
    0.47
     Whey
    0.47
    Activations Density 0.000%

    No Known Activations