© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40589
    Prev
    Next
    INDEX
    Explanations

    Indian states

    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_11_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
    awara
    0.57
    _{*}(
    0.54
    arnataka
    0.53
    هم
    0.52
     في
    0.52
     मुकाबले
    0.51
    ん
    0.50
    ፡፡
    0.50
     guerras
    0.50
    ي
    0.50
    POSITIVE LOGITS
     note
    0.57
     as
    0.56
     but
    0.54
     harga
    0.54
     key
    0.53
     प्रा
    0.53
    utilizzo
    0.52
     sélection
    0.50
     anbef
    0.49
     figure
    0.49
    Activations Density 0.001%

    No Known Activations