© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196636
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_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
     சுண்ணா
    0.43
     밤
    0.42
    मलव
    0.42
     ಸೇವ
    0.41
     വൃ
    0.40
     Бал
    0.39
    Celltype
    0.39
     cuticle
    0.38
     guardar
    0.38
     travertine
    0.38
    POSITIVE LOGITS
     disconnect
    0.43
     shortcomings
    0.43
     flaws
    0.41
    Ext
    0.40
     complexities
    0.39
    ideen
    0.38
    õ
    0.38
     failings
    0.38
    on
    0.37
     killings
    0.37
    Activations Density 0.000%

    No Known Activations