© 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. 202618
    Prev
    Next
    INDEX
    Explanations

    machine learning

    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
    Y
    1.14
    \
    1.01
    är
    0.98
     to
    0.94
    é
    0.91
    OL
    0.89
    ë
    0.87
    J
    0.85
    EW
    0.82
    AO
    0.81
    POSITIVE LOGITS
    1
    1.00
     envoy
    0.93
    ני
    0.92
     individui
    0.89
     esterno
    0.88
    }$.
    0.86
    n
    0.86
     altro
    0.85
    ।
    0.84
     incarnation
    0.84
    Activations Density 0.004%

    No Known Activations