© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165730
    Prev
    Next
    INDEX
    Explanations

    comma followed by a word

    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_31_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
     despite
    0.41
     malgré
    0.40
    即使
    0.38
     meskipun
    0.34
    雖
    0.34
    Despite
    0.32
     nonostante
    0.32
     Despite
    0.32
     apesar
    0.32
    雖然
    0.32
    POSITIVE LOGITS
    এ
    0.30
    ched
    0.29
    yns
    0.29
    ลด
    0.28
    stalk
    0.27
    oods
    0.27
    using
    0.27
    ച്ച്
    0.27
     தொழி
    0.27
    ths
    0.26
    Activations Density 0.031%

    No Known Activations