© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23576
    Prev
    Next
    INDEX
    Explanations

    proper names

    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_56_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
    ⁱ
    0.44
    AMENT
    0.41
     আধ
    0.39
     encontrados
    0.39
    氏は
    0.39
    ISTR
    0.39
    ək
    0.37
    较
    0.37
    amental
    0.36
     moveTo
    0.36
    POSITIVE LOGITS
    corona
    0.39
     Corona
    0.38
     kind
    0.37
    target
    0.37
    ńca
    0.37
    kind
    0.36
    jones
    0.36
     Cesar
    0.36
    cosity
    0.36
    teenage
    0.35
    Activations Density 0.010%

    No Known Activations