© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176612
    Prev
    Next
    INDEX
    Explanations

    cities and national capitals

    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_24_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
     ignoreString
    0.41
     העולם
    0.37
    Ⓡ
    0.37
    ,...,
    0.37
     ioutil
    0.37
     అను
    0.36
    ških
    0.36
    捚
    0.36
     مطلق
    0.35
     지금까지
    0.35
    POSITIVE LOGITS
    isia
    0.43
    Liverpool
    0.41
     Aleppo
    0.40
    upu
    0.38
    Madrid
    0.36
    IKO
    0.36
    רק
    0.36
     Khartoum
    0.36
    legs
    0.36
     Damascus
    0.36
    Activations Density 0.001%

    No Known Activations