© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231886
    Prev
    Next
    INDEX
    Explanations

    builder method calls

    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
    0
    1.11
    hwar
    0.95
    uls
    0.87
    ientos
    0.86
    ot
    0.85
    8
    0.85
    oti
    0.84
     отношений
    0.81
    ver
    0.79
    ott
    0.79
    POSITIVE LOGITS
    s
    1.15
    t
    1.09
    of
    0.98
    "，
    0.93
    تها
    0.92
    ై
    0.91
    </tr>
    0.91
     ContentView
    0.91
    ي
    0.89
     be
    0.89
    Activations Density 0.000%

    No Known Activations