© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89586
    Prev
    Next
    INDEX
    Explanations

    carbon

    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_11_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
    r
    0.49
    р
    0.42
    n
    0.42
    ร
    0.41
     Williamsburg
    0.38
    ר
    0.38
     fling
    0.38
     Dietary
    0.37
    Mutability
    0.36
    t
    0.36
    POSITIVE LOGITS
    ூரில்
    0.38
     cinquième
    0.37
    航空公司
    0.37
    vector
    0.36
    災
    0.35
    ີ້
    0.35
    érir
    0.35
    卓
    0.35
    찍
    0.34
     deuxième
    0.34
    Activations Density 0.003%

    No Known Activations