© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29641
    Prev
    Next
    INDEX
    Explanations

    estimator or estimate

    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_10_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
    ylmethylsulfanyl
    0.89
    اتی
    0.85
    ون
    0.80
    </h2>
    0.76
    ]}$.
    0.75
    ่
    0.75
    ্ত
    0.73
    </h3>
    0.73
    त्मक
    0.71
    atek
    0.71
    POSITIVE LOGITS
     in
    1.34
     estimate
    1.17
    Estim
    1.12
    Estimate
    1.10
     في
    1.01
    0
    1.01
    in
    1.00
     Estimate
    0.95
    estimate
    0.92
     estima
    0.91
    Activations Density 0.007%

    No Known Activations