© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 118249
    Prev
    Next
    INDEX
    Explanations

    event listener management

    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_27_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
     increments
    0.41
     O
    0.39
    ekten
    0.38
     Katt
    0.38
    טע
    0.37
     کمپ
    0.35
     OSC
    0.35
     equivalence
    0.34
    ätten
    0.34
    貓
    0.34
    POSITIVE LOGITS
     salud
    0.42
    PrototypeOf
    0.40
    Forgot
    0.40
    噰
    0.40
    airro
    0.39
     ஆரோக்கிய
    0.39
    项目
    0.39
    ago
    0.39
    க்கூடாது
    0.39
     پیشہ
    0.38
    Activations Density 0.001%

    No Known Activations