© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44602
    Prev
    Next
    INDEX
    Explanations

    explicitly prohibit

    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_13_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
     Bus
    0.56
     Barley
    0.54
    </em>
    0.53
    </strong>
    0.51
     Fram
    0.51
     Goodbye
    0.51
    зал
    0.51
     Honour
    0.50
    CodeDom
    0.50
    
    0.49
    POSITIVE LOGITS
     automatiquement
    0.63
     sprawl
    0.58
     automáticamente
    0.57
    cence
    0.54
    cimentos
    0.54
     chiral
    0.53
    SignedIn
    0.53
     debris
    0.53
     adiabatic
    0.52
     jquery
    0.52
    Activations Density 0.010%

    No Known Activations