© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7593
    Prev
    Next
    INDEX
    Explanations

    counting epoch/loss

    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_40_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
    骛
    0.44
     ма
    0.38
     caul
    0.38
    lasses
    0.38
     linha
    0.37
     ma
    0.37
    bender
    0.36
     varying
    0.36
     ჭ
    0.35
    ໜ
    0.35
    POSITIVE LOGITS
     Lions
    0.55
    Lion
    0.52
     Lion
    0.50
    British
    0.50
     interception
    0.45
     intercept
    0.45
    lions
    0.45
    獅
    0.44
    british
    0.44
    lion
    0.43
    Activations Density 0.005%

    No Known Activations