© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 241967
    Prev
    Next
    INDEX
    Explanations

    become increasingly

    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_25_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
     princesa
    0.30
    зяй
    0.29
     )-
    0.28
     जमान
    0.27
     wearables
    0.27
     princesses
    0.27
     currentState
    0.27
     ekonomi
    0.26
    ทะ
    0.26
     förs
    0.26
    POSITIVE LOGITS
    这本书
    0.31
    关于
    0.28
    Year
    0.27
    關於
    0.27
    chapter
    0.26
    },
    0.26
    yn
    0.26
    acheal
    0.26
     duo
    0.26
    ampton
    0.26
    Activations Density 0.010%

    No Known Activations