© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9232
    Prev
    Next
    INDEX
    Explanations

    superlatives followed by positive outcomes

    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_13_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
     n
    0.40
    nda
    0.39
    三个
    0.37
    }=\
    0.36
    স
    0.35
     MORE
    0.34
    nrow
    0.34
    infty
    0.34
    THREE
    0.33
     bloco
    0.33
    POSITIVE LOGITS
     Katie
    0.42
     生地
    0.42
     сведения
    0.40
     作業
    0.40
     않았
    0.40
     片
    0.40
     πληροφο
    0.40
    ական
    0.39
     Suche
    0.39
     kttt
    0.39
    Activations Density 0.088%

    No Known Activations