© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62746
    Prev
    Next
    INDEX
    Explanations

    语言问候

    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
    Negative Logits
    y
    1.42
    ین
    1.41
    ა
    1.41
    ம்
    1.39
    f
    1.35
    یی
    1.34
    i
    1.31
    ன்
    1.23
    ח
    1.20
    й
    1.14
    POSITIVE LOGITS
    '
    2.48
    "
    1.59
    }
    1.52
    .
    1.41
    }).
    1.24
    的
    1.21
    }.
    1.16
    )
    1.16
                    
    1.13
    ियों
    1.13
    Activations Density 0.000%

    No Known Activations