© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159002
    Prev
    Next
    INDEX
    Explanations

    lady and Lazy

    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_2_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
    iu
    0.98
    ש
    0.87
    arj
    0.82
    arjo
    0.79
    t
    0.79
    nels
    0.77
    ט
    0.77
    মূলক
    0.76
    ৪
    0.76
    ३
    0.76
    POSITIVE LOGITS
    I
    1.28
     was
    1.20
    "
    1.10
    </h2>
    0.93
    ص
    0.89
    )
    0.86
    不
    0.83
    '
    0.82
    </h4>
    0.81
    ]
    0.81
    Activations Density 0.001%

    No Known Activations