© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193883
    Prev
    Next
    INDEX
    Explanations

    capabilities, limitations, and diversity of

    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_27_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
    AttributeInfo
    0.37
     باغ
    0.36
    ူ
    0.35
    上下文
    0.34
     beam
    0.33
     gardens
    0.33
     bagaimana
    0.33
     probiotic
    0.33
     lattices
    0.32
     clearContext
    0.32
    POSITIVE LOGITS
     Alg
    0.40
    ആ
    0.39
     Healthy
    0.38
     P
    0.37
     Pays
    0.37
     Sierra
    0.37
     Z
    0.36
     Sig
    0.35
     Essential
    0.35
     G
    0.35
    Activations Density 0.001%

    No Known Activations