© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 67825
    Prev
    Next
    INDEX
    Explanations

    places and geography

    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_46_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
    Ча
    0.39
    hip
    0.38
    牽
    0.38
    ship
    0.38
    actually
    0.37
    酉
    0.37
    ✋
    0.37
    MOR
    0.37
    切实
    0.36
    ☝
    0.36
    POSITIVE LOGITS
     lind
    0.46
     Laur
    0.42
     Kass
    0.42
     activation
    0.41
     balance
    0.41
     Gond
    0.39
     dele
    0.39
     Emotional
    0.39
    omitempty
    0.38
     relaxation
    0.38
    Activations Density 0.039%

    No Known Activations