© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130630
    Prev
    Next
    INDEX
    Explanations

    search query

    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_6_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
    }></
    1.01
    ;}
    1.00
     Wählen
    0.89
    យើង
    0.89
    ंना
    0.88
    },
    0.84
    führer
    0.84
    }\,\
    0.84
    ;</
    0.83
    جين
    0.82
    POSITIVE LOGITS
    ל
    1.29
     for
    1.20
    ר
    1.20
    ล
    1.16
    л
    1.13
    д
    1.13
     on
    1.09
    ร
    1.02
    ы
    1.01
     can
    1.00
    Activations Density 0.008%

    No Known Activations