© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123844
    Prev
    Next
    INDEX
    Explanations

    Sudanese, Sucre

    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_3_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
    使
    0.66
    F
    0.64
     információ
    0.60
    其他
    0.59
    ít
    0.55
    ug
    0.55
     मैचों
    0.55
    用心
    0.55
    N
    0.54
     విశ్వ
    0.54
    POSITIVE LOGITS
     ৭
    0.79
    chodzi
    0.79
     (
    0.76
     ۳
    0.76
     Р
    0.75
    ي
    0.75
     ৩
    0.75
    ię
    0.74
    ים
    0.74
    ną
    0.74
    Activations Density 0.000%

    No Known Activations