© 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. 10826
    Prev
    Next
    INDEX
    Explanations

    measurements and units

    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
    CHN
    0.42
    illy
    0.38
    েলে
    0.36
    Thr
    0.36
    සේ
    0.34
    咧
    0.34
    cey
    0.34
     Bolívar
    0.34
    ጅ
    0.34
     Bold
    0.33
    POSITIVE LOGITS
    তাব
    0.42
    Pricing
    0.40
    ิง
    0.38
    distan
    0.38
     koniec
    0.38
    ینے
    0.37
    Messaging
    0.37
    Morse
    0.36
     Su
    0.35
    ंधर
    0.35
    Activations Density 0.081%

    No Known Activations