© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 238195
    Prev
    Next
    INDEX
    Explanations

    jsonplaceholder.typicode.com/todos

    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
     DIA
    0.41
     crashes
    0.37
     crashed
    0.36
     PUR
    0.36
     _____________
    0.35
     weaken
    0.35
     ____________
    0.35
     Dia
    0.34
     likewise
    0.34
    ____________
    0.33
    POSITIVE LOGITS
    ressor
    0.39
     ناخد
    0.38
    माजिक
    0.37
    æg
    0.37
    udiant
    0.36
    équipe
    0.36
    æl
    0.35
     utilización
    0.35
    ït
    0.35
    hydrocèle
    0.35
    Activations Density 0.001%

    No Known Activations