© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 92057
    Prev
    Next
    INDEX
    Explanations

    alexa turns

    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
    Negative Logits
     اي
    1.02
     fijo
    0.95
     indépend
    0.93
    ت
    0.88
     живот
    0.88
     energético
    0.87
     ي
    0.86
     دي
    0.86
    يد
    0.84
     живота
    0.84
    POSITIVE LOGITS
    )
    0.93
    ]
    0.89
    ک
    0.87
    }
    0.84
    та
    0.78
    ின்
    0.73
    ’)
    0.73
    utors
    0.73
    िड
    0.73
    ların
    0.71
    Activations Density 0.000%

    No Known Activations