© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 15562
    Prev
    Next
    INDEX
    Explanations

    lightning Trainer

    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
    angnya
    0.64
    اب
    0.59
    نګه
    0.59
    𝑟
    0.58
    r
    0.57
     próprio
    0.55
     خپل
    0.55
    ng
    0.55
    čních
    0.55
     própria
    0.55
    POSITIVE LOGITS
    <sup>
    0.53
    )
    0.52
     Bolivia
    0.52
     leftist
    0.50
     teacher
    0.50
     similarly
    0.49
    </td>
    0.47
     Jesuit
    0.47
    Tuesday
    0.46
    Wednesday
    0.46
    Activations Density 0.004%

    No Known Activations