© 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. 10045
    Prev
    Next
    INDEX
    Explanations

    lanterns and Marriott hotels

    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
    Genero
    0.54
     اختيار
    0.53
    Tabla
    0.52
    Bue
    0.52
    ñ
    0.50
     scelta
    0.49
    Guide
    0.49
    [-]
    0.49
     asing
    0.48
    検索
    0.48
    POSITIVE LOGITS
    queline
    0.51
     perverse
    0.50
    ied
    0.50
    zić
    0.49
     worry
    0.48
    itsky
    0.48
    ?“
    0.47
    :“
    0.47
    dum
    0.46
    preuve
    0.46
    Activations Density 0.008%

    No Known Activations