© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28289
    Prev
    Next
    INDEX
    Explanations

    save, find, get

    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_40_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
     arreglo
    0.40
     پو
    0.40
     quotas
    0.39
    を加
    0.38
     quota
    0.38
     ylab
    0.37
    
    0.37
     स्थिर
    0.36
    
    0.36
     pengambilan
    0.36
    POSITIVE LOGITS
     FMC
    0.47
     first
    0.44
     bring
    0.42
     become
    0.38
     tell
    0.38
    ics
    0.38
    icol
    0.37
    acol
    0.37
     alk
    0.36
     통해서
    0.36
    Activations Density 0.000%

    No Known Activations