© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12229
    Prev
    Next
    INDEX
    Explanations

    PC Part Picker, Tech, LTT, SCP

    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_13_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
    ంశ
    0.54
    boxed
    0.51
    dimensioni
    0.51
     punti
    0.50
    requirement
    0.49
    borderwidth
    0.49
    權
    0.49
    dims
    0.48
     مزاج
    0.48
    points
    0.48
    POSITIVE LOGITS
     investigate
    0.51
     jon
    0.51
     contaminated
    0.49
    ד
    0.48
     γ
    0.48
     investigates
    0.47
    मन
    0.47
     gasolina
    0.46
    یه
    0.46
     decontamination
    0.46
    Activations Density 0.023%

    No Known Activations