© 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. 159056
    Prev
    Next
    INDEX
    Explanations

    Madam titles or names

    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
    <0x0D>
    1.67
    </h2>
    1.39
    </h3>
    1.34
     are
    1.17
    ↵
    1.13
     Её
    1.09
    </code>
    1.05
    2
    1.02
    </h4>
    1.01
    </em>
    0.99
    POSITIVE LOGITS
    ac
    1.14
    ла
    1.12
    y
    1.08
    ت
    1.05
    ED
    1.02
    gli
    0.99
    IA
    0.97
     it
    0.96
    rals
    0.95
    rée
    0.93
    Activations Density 0.000%

    No Known Activations