© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 5528
    Prev
    Next
    INDEX
    Explanations

    specific terms or concepts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    вершена
    0.39
    ainless
    0.39
     Bite
    0.39
    Load
    0.38
    DUCT
    0.38
    leukin
    0.38
     সপ্ত
    0.37
    현
    0.37
     Seth
    0.36
    ੁਰ
    0.36
    POSITIVE LOGITS
    reetype
    0.42
    bracketing
    0.38
     initiator
    0.38
    ty
    0.37
     Kapoor
    0.37
    จับ
    0.37
    encja
    0.37
    Gy
    0.37
    టే
    0.37
     directive
    0.36
    Activations Density 0.007%

    No Known Activations