© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 195489
    Prev
    Next
    INDEX
    Explanations

    superhero characters

    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_46_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Batman
    1.65
     batman
    1.61
    Batman
    1.59
     bat
    1.37
    Bat
    1.37
     Bat
    1.36
    蝙
    1.33
     BAT
    1.30
    bat
    1.23
    BAT
    1.23
    POSITIVE LOGITS
     Jennie
    0.42
    ந்திய
    0.42
     ایرانی
    0.40
     Obrig
    0.39
    Jenn
    0.38
    AdapterView
    0.38
    hões
    0.38
    anesulf
    0.37
    ]_
    0.36
    ATTLE
    0.36
    Activations Density 0.000%

    No Known Activations