© 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. 14734
    Prev
    Next
    INDEX
    Explanations

    title

    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
     KAHN
    0.48
    ۥ
    0.45
     Khan
    0.41
     Kenyatta
    0.41
    })$.
    0.41
     сол
    0.40
     Algonquin
    0.40
     Bonaparte
    0.40
     д
    0.40
     Sartre
    0.39
    POSITIVE LOGITS
    ể
    0.44
    ुरे
    0.43
    י
    0.41
    摸
    0.41
    Ses
    0.40
    Tens
    0.37
    Wood
    0.37
    稠
    0.37
     by
    0.36
    achten
    0.36
    Activations Density 0.044%

    No Known Activations