© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 232861
    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_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
     suicide
    0.41
    కుంది
    0.41
    岱
    0.41
    ेज
    0.39
    Practice
    0.38
    anthemum
    0.38
     ZOOM
    0.38
     Zoom
    0.37
     ड्रीम
    0.37
     "'.$
    0.37
    POSITIVE LOGITS
    opar
    0.42
     hil
    0.40
     метр
    0.38
     opacity
    0.38
    ibu
    0.37
    앜
    0.37
    цах
    0.37
     leads
    0.36
     fond
    0.36
     Ib
    0.35
    Activations Density 0.000%

    No Known Activations