© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209487
    Prev
    Next
    INDEX
    Explanations

    PHP $_SERVER variables

    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_20_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
     filosofia
    0.48
    于是
    0.46
    𒊩
    0.46
     फैक्ट्री
    0.45
     XS
    0.44
     филосо
    0.44
     ライ
    0.44
     운동
    0.43
     alrededores
    0.43
     tanıt
    0.42
    POSITIVE LOGITS
     forceful
    0.47
     broadcaster
    0.43
     ख
    0.43
     rebellious
    0.42
     enigmatic
    0.42
     overrated
    0.42
     ordinary
    0.41
    np
    0.41
     publisher
    0.41
     number
    0.40
    Activations Density 0.000%

    No Known Activations