© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215736
    Prev
    Next
    INDEX
    Explanations

    define what we mean

    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
     जमान
    0.41
     Officials
    0.40
     pptn
    0.39
     coment
    0.39
     Į
    0.38
     cheesecake
    0.38
    ಲ್‌
    0.37
    lass
    0.37
     initiator
    0.37
     officials
    0.37
    POSITIVE LOGITS
     وتح
    0.44
    AO
    0.40
     Pavlov
    0.38
    BO
    0.38
    格子
    0.37
    絢
    0.37
    QR
    0.36
    UW
    0.36
    Jurassic
    0.36
    និ
    0.35
    Activations Density 0.003%

    No Known Activations