© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 240939
    Prev
    Next
    INDEX
    Explanations

    loves to

    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_25_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
     neuromuscular
    0.38
     different
    0.36
     statesmen
    0.36
    不一樣
    0.35
    市镇
    0.35
     badass
    0.35
     Bradshaw
    0.35
    珢
    0.34
    ériment
    0.34
     fiery
    0.34
    POSITIVE LOGITS
    的双
    0.40
    क्ले
    0.39
     procurar
    0.39
     abierta
    0.38
     año
    0.38
     sceGu
    0.37
    ptica
    0.37
    渫
    0.37
     años
    0.36
    ².
    0.36
    Activations Density 0.001%

    No Known Activations