© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193612
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_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
    耱
    0.49
    aparikkh
    0.48
    ༸
    0.48
     নাঁ
    0.47
    ⸩
    0.47
    Therates
    0.46
     বুকের
    0.45
    nCurr
    0.45
    akkhati
    0.44
    Coins
    0.44
    POSITIVE LOGITS
    0.51
     one
    0.46
     c
    0.42
     &
    0.41
     service
    0.39
     knowledge
    0.39
     idea
    0.38
     kim
    0.38
     s
    0.37
     summer
    0.36
    Activations Density 0.000%

    No Known Activations