© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 5956
    Prev
    Next
    INDEX
    Explanations

    desc, disc, and transcend prefixes

    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_40_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
    Exhibit
    0.39
     Exhibit
    0.38
    //@
    0.37
     Exhibits
    0.36
    <0xB0>
    0.35
     issued
    0.35
    棫
    0.35
    Slug
    0.35
     przen
    0.35
    㖪
    0.35
    POSITIVE LOGITS
     desc
    0.54
     Desc
    0.48
    desc
    0.47
    Desc
    0.47
     descend
    0.45
    Disc
    0.44
    anso
    0.44
    disc
    0.43
     descended
    0.41
    ence
    0.40
    Activations Density 0.060%

    No Known Activations