© 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. 208144
    Prev
    Next
    INDEX
    Explanations

    differentiable everywhere sorting methods

    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
     schnelle
    0.20
     کنگ
    0.20
     enhancement
    0.20
     മുന്‍
    0.20
     Potential
    0.20
     Där
    0.20
    ...
    0.19
    警
    0.19
    声
    0.19
     क्विक
    0.19
    POSITIVE LOGITS
    bant
    0.23
    ionat
    0.22
    heiro
    0.22
    esgue
    0.22
     derin
    0.22
     vip
    0.21
     valu
    0.21
     temperat
    0.21
     dut
    0.21
    িয়ান
    0.21
    Activations Density 0.002%

    No Known Activations