© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161195
    Prev
    Next
    INDEX
    Explanations

    HAARP, Ulaanbaatar, city names

    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_2_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
    al
    1.48
    2
    1.43
    1
    1.23
    el
    1.06
    ى
    1.02
    }$
    1.00
    س
    0.97
    ن
    0.95
    art
    0.93
    ed
    0.93
    POSITIVE LOGITS
    the
    1.16
    м
    1.00
     pubblici
    0.95
     запрос
    0.93
     surgi
    0.92
    т
    0.92
    ва
    0.91
     служ
    0.91
     выбра
    0.90
     equivoc
    0.90
    Activations Density 0.000%

    No Known Activations