© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 177814
    Prev
    Next
    INDEX
    Explanations

    formerly, previously, historically

    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_29_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
     अंतराल
    0.40
    焽
    0.40
    綽
    0.37
     качества
    0.37
     compost
    0.37
     abilities
    0.36
     अच्छे
    0.36
     normality
    0.36
    ቝ
    0.36
     ponctu
    0.36
    POSITIVE LOGITS
     obecnie
    0.41
    现在
    0.41
     jetzt
    0.40
     сейчас
    0.40
     maintenant
    0.40
     现在
    0.40
     geçen
    0.40
    ール
    0.39
    昨年
    0.39
     statutory
    0.39
    Activations Density 0.007%

    No Known Activations