© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 147685
    Prev
    Next
    INDEX
    Explanations

    the

    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
     far
    1.03
    far
    0.82
     Far
    0.71
    Far
    0.71
     FAR
    0.68
    FAR
    0.66
     фар
    0.62
    远
    0.57
    фар
    0.56
     jauh
    0.50
    POSITIVE LOGITS
     landscape
    0.98
    landscape
    0.87
    Landscape
    0.83
     landscapes
    0.82
     Landscape
    0.79
     paisaje
    0.77
     paysage
    0.77
     paes
    0.75
     paisajes
    0.73
     Landscapes
    0.66
    Activations Density 0.005%

    No Known Activations