© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 193645
    Prev
    Next
    INDEX
    Explanations

    }

    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_15_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
    ﮢ
    0.51
     subcutaneous
    0.46
    ﮈ
    0.44
    xcsche
    0.43
     demostrar
    0.43
    removeClass
    0.42
     thuần
    0.41
    Halloween
    0.41
     letz
    0.40
     macroscopic
    0.39
    POSITIVE LOGITS
     помі
    0.52
     theorists
    0.51
     Bitte
    0.49
     Theor
    0.48
     groupes
    0.48
     ciri
    0.47
    迠
    0.47
     linge
    0.46
    millimeters
    0.46
     Unesco
    0.46
    Activations Density 0.000%

    No Known Activations