© 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. 29180
    Prev
    Next
    INDEX
    Explanations

    dolphin, dolphins

    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
     is
    0.73
    igheder
    0.70
     .”
    0.69
    inien
    0.66
     .
    0.66
    kten
    0.66
     ;
    0.64
    obile
    0.63
     ፡፡
    0.62
    kker
    0.62
    POSITIVE LOGITS
     dolphin
    0.89
    ش
    0.86
     dolphins
    0.83
    sh
    0.78
    یا
    0.77
    า
    0.75
    dolphin
    0.74
    د
    0.74
    ει
    0.73
    </h2>
    0.72
    Activations Density 0.004%

    No Known Activations