© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50660
    Prev
    Next
    INDEX
    Explanations

    resources listed at end section

    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_30_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
     mencionó
    0.32
     పేర్కొ
    0.31
     করেছে
    0.30
    Спољашње
    0.29
     vuccanti
    0.29
     vutta
    0.28
     mentioned
    0.28
     >>=
    0.28
     menciona
    0.28
    Injector
    0.27
    POSITIVE LOGITS
    続く
    0.30
     upcoming
    0.29
    ateg
    0.29
    ivil
    0.28
    ими
    0.28
     இனி
    0.28
    രിക്കും
    0.28
    eek
    0.28
     unaffected
    0.28
    iiii
    0.28
    Activations Density 0.031%

    No Known Activations