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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230092
    Prev
    Next
    INDEX
    Explanations

    transitioning

    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_6_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
    ب
    1.84
    ي
    1.52
    ق
    1.28
     on
    1.26
    ف
    1.25
    on
    1.19
     aumentó
    1.08
    is
    1.07
    મ
    1.05
    يّ
    1.05
    POSITIVE LOGITS
    =
    0.85
     februari
    0.83
     powied
    0.82
    <
    0.82
    ;
    0.79
        
    0.79
     ofApp
    0.78
     =
    0.77
    ).
    0.77
     september
    0.76
    Activations Density 0.000%

    No Known Activations