© 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. 1480
    Prev
    Next
    INDEX
    Explanations

    Telegraph days

    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
    פל
    0.45
    Qt
    0.42
    proximity
    0.41
    涨
    0.39
    acos
    0.38
     Bg
    0.37
    PL
    0.36
    ग्राम
    0.36
     পর্যায়ের
    0.36
    漲
    0.35
    POSITIVE LOGITS
     Telegraph
    0.60
     telegraph
    0.49
     tắt
    0.43
     டை
    0.41
     যাচ্ছিল
    0.40
     তে
    0.39
    haviours
    0.39
    柳
    0.38
     हालाँकि
    0.37
     scalar
    0.36
    Activations Density 0.001%

    No Known Activations