© 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. 5932
    Prev
    Next
    INDEX
    Explanations

    above and beyond

    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
    㧿
    0.24
    ).(
    0.24
     යුතුය
    0.24
    㫴
    0.23
    𐰚
    0.23
    㬰
    0.23
    ானது
    0.23
     মহাশয়ের
    0.23
    платно
    0.22
    拁
    0.22
    POSITIVE LOGITS
     div
    0.21
    $$
    0.21
     ,
    0.21
     portrait
    0.20
     Conf
    0.20
    g
    0.20
    °
    0.20
    loading
    0.20
     Qur
    0.20
    WithValue
    0.20
    Activations Density 0.052%

    No Known Activations