© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156708
    Prev
    Next
    INDEX
    Explanations

    Abkhazia and South Ossetia

    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_2_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
    м
    1.27
    ном
    1.09
    qu
    1.04
    ون
    1.03
    де
    1.01
    स
    0.99
    наче
    0.99
    fight
    0.96
    ன்
    0.96
    enfants
    0.96
    POSITIVE LOGITS
     is
    1.29
    1.24
    2
    1.06
     it
    0.99
    را
    0.96
     )
    0.95
     t
    0.92
     }
    0.90
    ৬
    0.89
     on
    0.86
    Activations Density 0.000%

    No Known Activations