© 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. 206553
    Prev
    Next
    INDEX
    Explanations

    entertaining streams, lie, ride, titles

    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
    ส
    1.15
            
    0.98
     metadata
    0.94
    AT
    0.93
    0
    0.93
     modifier
    0.91
    AN
    0.90
     resistor
    0.89
     diaspora
    0.85
    Are
    0.84
    POSITIVE LOGITS
     ﺍ
    1.12
    q
    1.08
    σε
    1.07
    \,\
    1.05
     அளி
    1.02
    ير
    1.02
    ية
    1.00
    wijl
    0.99
    مركز
    0.99
     ancienne
    0.98
    Activations Density 0.000%

    No Known Activations