© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 213248
    Prev
    Next
    INDEX
    Explanations

    fully

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
    ][_
    0.40
    }}_{
    0.38
    }}_{\
    0.37
    ]++;
    0.36
    }_{{\
    0.36
     Tot
    0.35
    និយ
    0.35
    Totals
    0.34
    CrossRef
    0.34
    <sub>
    0.34
    POSITIVE LOGITS
     fully
    2.36
     Fully
    2.03
    Fully
    1.95
     pleinement
    1.62
    fully
    1.48
     полностью
    1.48
     FULL
    1.46
    FULLY
    1.45
     повністю
    1.31
     full
    1.20
    Activations Density 0.001%

    No Known Activations