© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 131647
    Prev
    Next
    INDEX
    Explanations

    AUTOSAR platforms and environments

    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
    (
    1.02
    ir
    0.98
    n
    0.95
    that
    0.92
    fortunate
    0.86
    ल्पनिक
    0.86
    ]}
    0.85
    Expense
    0.84
    spending
    0.84
    Battery
    0.84
    POSITIVE LOGITS
    ä
    1.00
     from
    0.97
     to
    0.96
     was
    0.95
     k
    0.93
     paradigm
    0.92
    0.92
     c
    0.87
     divulg
    0.87
     nov
    0.86
    Activations Density 0.000%

    No Known Activations