© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2613
    Prev
    Next
    INDEX
    Explanations

    Jupyter IPython Notebook

    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_39_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
     Función
    0.39
    𝘂
    0.38
    ওয়াল
    0.35
    arkeit
    0.35
     pecho
    0.35
    𝒖
    0.35
     ที
    0.34
    𝗧
    0.34
    䨘
    0.34
    ட்டை
    0.34
    POSITIVE LOGITS
    gement
    0.40
     chief
    0.37
     vt
    0.36
     System
    0.35
     imp
    0.35
     tact
    0.35
    buk
    0.34
    ipy
    0.34
     signalling
    0.34
     help
    0.33
    Activations Density 0.024%

    No Known Activations