© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 125461
    Prev
    Next
    INDEX
    Explanations

    the letter d followed by parentheses

    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_37_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
     छोट
    0.40
     booked
    0.39
    inp
    0.39
     fas
    0.38
    ỵ
    0.38
    vad
    0.37
     zase
    0.37
    ্ৰ
    0.37
     xwe
    0.37
    感恩
    0.37
    POSITIVE LOGITS
    的部分
    0.40
    (($
    0.38
    ongyang
    0.38
    ляция
    0.37
     Communic
    0.37
    Clinton
    0.36
     बढ़ता
    0.36
    それに
    0.35
    "].
    0.35
    Medit
    0.35
    Activations Density 0.002%

    No Known Activations