© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 122071
    Prev
    Next
    INDEX
    Explanations

    available or starting

    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_37_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
     decade
    0.41
     заранее
    0.41
     ಎಲ್ಲಾ
    0.40
    lia
    0.38
     प्रजा
    0.38
    Started
    0.37
    🚗
    0.37
     Chia
    0.37
    所有
    0.36
     false
    0.35
    POSITIVE LOGITS
     endocr
    0.37
    泯
    0.37
    Tamil
    0.36
    elics
    0.36
    alamu
    0.35
     Zionist
    0.35
     helfen
    0.35
    抵达
    0.34
    ამართ
    0.34
     తమిళ
    0.34
    Activations Density 0.000%

    No Known Activations