© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12812
    Prev
    Next
    INDEX
    Explanations

    topography features

    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_13_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
    á
    0.59
    weeks
    0.51
    í
    0.49
     Raja
    0.48
    ā
    0.48
    %,
    0.48
    ds
    0.48
    ė
    0.47
     Enth
    0.47
    ­
    0.47
    POSITIVE LOGITS
     hillside
    0.59
     hill
    0.55
     gradient
    0.52
    旖
    0.52
     mountain
    0.52
     scan
    0.48
     山
    0.48
     foothills
    0.48
     hilltop
    0.46
     substituent
    0.46
    Activations Density 0.024%

    No Known Activations