© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6410
    Prev
    Next
    INDEX
    Explanations

    authentication type

    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
    pade
    0.26
     коля
    0.22
    andoah
    0.21
     HUB
    0.21
    霑
    0.21
     hairdry
    0.20
    jekt
    0.20
    ্যন্তরীণ
    0.19
     hairline
    0.19
    akyReLU
    0.19
    POSITIVE LOGITS
    Government
    0.21
     Blocks
    0.21
    Blocks
    0.21
     चाहे
    0.21
    oine
    0.20
     Config
    0.20
     sample
    0.20
    革
    0.20
    Sample
    0.20
    Sof
    0.20
    Activations Density 0.011%

    No Known Activations