© 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. 37017
    Prev
    Next
    INDEX
    Explanations

    New York Times

    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
     inhomogeneities
    0.66
    𒊬
    0.59
     سين
    0.57
     δο
    0.56
    ঽ
    0.56
     étudiants
    0.55
     paradigms
    0.55
     interfacial
    0.54
     opcion
    0.54
     softens
    0.54
    POSITIVE LOGITS
    v
    0.55
     #
    0.53
     Figure
    0.49
     Protection
    0.48
     {
    0.48
     Security
    0.48
    k
    0.47
    t
    0.46
     Proper
    0.46
    telling
    0.46
    Activations Density 0.009%

    No Known Activations