© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 100533
    Prev
    Next
    INDEX
    Explanations

    Beverly Hills, Kyle, Stan

    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_14_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
    У
    0.66
    у
    0.65
    ر
    0.60
    ૂ
    0.60
    р
    0.59
    r
    0.59
    И
    0.55
    ي
    0.53
    re
    0.52
    и
    0.52
    POSITIVE LOGITS
     EXPERIENCE
    0.55
     Icons
    0.52
     AcOH
    0.52
     ivvu
    0.52
    <unused407>
    0.52
     tombs
    0.50
     AMOLED
    0.50
     Khmer
    0.50
    icals
    0.50
     Bxb
    0.50
    Activations Density 0.000%

    No Known Activations