© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23189
    Prev
    Next
    INDEX
    Explanations

    ，

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    acil
    0.44
    빻
    0.41
     ipv
    0.37
    ipv
    0.36
    Также
    0.36
     Casc
    0.36
    த்திலேயே
    0.35
    灞
    0.35
     bending
    0.34
     cordova
    0.33
    POSITIVE LOGITS
    可是
    2.38
     কিন্তু
    1.87
    만큼
    1.53
     কিন্ত
    1.48
     만큼
    1.46
     but
    1.34
    কিন্তু
    1.31
     But
    1.30
    but
    1.30
     pero
    1.27
    Activations Density 0.003%

    No Known Activations