© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5393
    Prev
    Next
    INDEX
    Explanations

    deflate, compression, collapse, decomp

    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
     perspici
    0.36
    𝓜
    0.35
    蔚
    0.35
    னோ
    0.35
    icklabels
    0.34
    ky
    0.34
     duplic
    0.34
    띄
    0.34
    ர்க்க
    0.34
    Nan
    0.33
    POSITIVE LOGITS
     def
    2.30
     deflation
    2.25
    defl
    2.06
     deflate
    2.00
     Def
    1.99
    Def
    1.90
    def
    1.64
     DEF
    1.40
     déf
    1.36
    DEF
    1.36
    Activations Density 0.055%

    No Known Activations