© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37633
    Prev
    Next
    INDEX
    Explanations

    legal, governmental, or policy context

    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
    d
    0.64
    dır
    0.61
    д
    0.60
    ció
    0.59
     admisión
    0.57
     đảm
    0.57
     ऐसे
    0.55
     विज्ञापन
    0.55
    ere
    0.55
    のように
    0.55
    POSITIVE LOGITS
    ی
    0.79
     melaksanakan
    0.60
    ભગ
    0.59
    szlig
    0.59
     immunology
    0.58
    -]
    0.57
     Been
    0.55
     Toen
    0.55
    羪
    0.55
    -)
    0.54
    Activations Density 0.008%

    No Known Activations