© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7212
    Prev
    Next
    INDEX
    Explanations

    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_39_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
    বার্গ
    0.48
    𝟘
    0.47
    vieve
    0.45
    ствует
    0.45
    ЕС
    0.44
     Walth
    0.44
    èbres
    0.44
    IEE
    0.42
    蚁
    0.42
     Punkte
    0.42
    POSITIVE LOGITS
    aka
    0.51
    yang
    0.48
    aku
    0.46
     Tai
    0.45
    long
    0.44
    intang
    0.44
    tai
    0.43
    wa
    0.42
     tai
    0.42
     samba
    0.42
    Activations Density 0.035%

    No Known Activations