© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 194523
    Prev
    Next
    INDEX
    Explanations

    various followed by words

    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_15_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
     habe
    0.53
     stressing
    0.53
     cinematic
    0.52
     bombarded
    0.51
     drilling
    0.50
     ther
    0.49
    :
    0.49
     das
    0.48
     drilled
    0.48
     swollen
    0.48
    POSITIVE LOGITS
    스를
    0.53
    </h3>
    0.51
    國
    0.51
    న్స్‌
    0.50
     Еўропы
    0.49
    總
    0.48
    車
    0.48
    スペイン
    0.47
    忓
    0.47
     Incent
    0.46
    Activations Density 0.000%

    No Known Activations