© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38199
    Prev
    Next
    INDEX
    Explanations

    purely for a specific purpose or quality

    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_11_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
     sliced
    0.53
     felled
    0.52
    ter
    0.52
     –
    0.51
     utilizando
    0.50
     readily
    0.49
     handful
    0.49
     styleUrls
    0.49
    mberg
    0.49
     modestly
    0.48
    POSITIVE LOGITS
    ᆫ
    0.59
    "،
    0.57
    াস
    0.57
    ן
    0.55
     Polarization
    0.54
    ﺎ
    0.53
    اتی
    0.52
    igungs
    0.52
    ﺄ
    0.52
    ар
    0.51
    Activations Density 0.003%

    No Known Activations