© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52268
    Prev
    Next
    INDEX
    Explanations

    SEC EDGAR filings

    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_30_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
    ⚖
    0.45
    দায়
    0.41
    साल
    0.41
    㖡
    0.41
    izde
    0.38
     نظامی
    0.37
    こんにちは
    0.36
     एर
    0.36
    悳
    0.36
     آمر
    0.35
    POSITIVE LOGITS
     biore
    0.38
     shareholder
    0.38
     filings
    0.37
     booklet
    0.37
     booklets
    0.37
     Booklet
    0.36
     filing
    0.36
     Rac
    0.36
     book
    0.35
     ceil
    0.35
    Activations Density 0.003%

    No Known Activations