© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 200313
    Prev
    Next
    INDEX
    Explanations

    back, neck, pockets

    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_37_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
     neck
    1.08
     Neck
    1.01
     collar
    0.97
     necks
    0.95
    Neck
    0.94
    neck
    0.89
    颈
    0.85
    脖
    0.84
     neckline
    0.81
     collars
    0.80
    POSITIVE LOGITS
    蓥
    0.44
    SIN
    0.40
    සි
    0.39
    ANSAS
    0.38
     Word
    0.38
     buen
    0.37
     WORD
    0.37
     SCREEN
    0.37
     सिन्हा
    0.37
    veloppement
    0.37
    Activations Density 0.033%

    No Known Activations