© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167376
    Prev
    Next
    INDEX
    Explanations

    Kenya, Tanzania, Nigeria

    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_31_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
    腿
    0.43
    ாரி
    0.41
    вол
    0.38
    Shell
    0.37
     bremsstrahlung
    0.37
    ضل
    0.36
     മൂല
    0.36
    olulu
    0.36
     discret
    0.35
    Է
    0.35
    POSITIVE LOGITS
     우리나라
    0.49
    ivating
    0.40
     placement
    0.40
     minority
    0.39
     interesting
    0.38
     hovering
    0.37
     ironic
    0.37
     perinatal
    0.36
    텟
    0.36
     Nigeria
    0.36
    Activations Density 0.001%

    No Known Activations