© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201829
    Prev
    Next
    INDEX
    Explanations

    to give/supply/unlock/understand

    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_12_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
    *",
    0.61
    z
    0.57
    sj
    0.53
    x
    0.53
    es
    0.52
    g
    0.51
    *.
    0.51
    nj
    0.50
     আপনাকে
    0.50
     všech
    0.50
    POSITIVE LOGITS
    </em>
    0.50
    )」
    0.48
    </strong>
    0.45
    のが
    0.44
     dismantled
    0.43
     transplanted
    0.43
     embargo
    0.42
     交換
    0.42
    ！」
    0.41
    」
    0.41
    Activations Density 0.033%

    No Known Activations