© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208930
    Prev
    Next
    INDEX
    Explanations

    index to token mapping

    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
    괘
    0.47
    textup
    0.45
     equate
    0.44
    ikl
    0.42
    iana
    0.42
    આ
    0.41
    ifiz
    0.41
     discontinuous
    0.40
     fixed
    0.39
     hout
    0.39
    POSITIVE LOGITS
     Depend
    0.45
     Reflect
    0.44
     உள்
    0.44
     ஒழு
    0.44
     రో
    0.43
     ойной
    0.42
    வதன்
    0.41
    玑
    0.40
     Depends
    0.40
    坭
    0.40
    Activations Density 0.002%

    No Known Activations