© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236981
    Prev
    Next
    INDEX
    Explanations

    percentages

    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_25_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
    纪
    0.18
     hissed
    0.18
     inadvertently
    0.17
     Há
    0.17
     নজরুল
    0.17
    朱
    0.16
     eureka
    0.16
     نفس
    0.16
     کھیلو
    0.16
    描き
    0.16
    POSITIVE LOGITS
     bestuur
    0.23
     billionaires
    0.22
    স্ত্র
    0.21
    connected
    0.21
     CEOs
    0.21
    ઢ
    0.20
     Milliarden
    0.20
     CEO
    0.20
     antipsych
    0.20
     twitch
    0.20
    Activations Density 0.001%

    No Known Activations