© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169422
    Prev
    Next
    INDEX
    Explanations

    B

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     sequestration
    0.40
    ield
    0.38
    requenz
    0.37
    uerung
    0.37
     sad
    0.36
     shale
    0.35
    荧
    0.35
     singers
    0.35
    aler
    0.35
    нков
    0.35
    POSITIVE LOGITS
     }^{+}
    0.46
    TR
    0.42
    Rt
    0.42
     RT
    0.39
     TR
    0.38
     चक
    0.38
     rt
    0.37
    வ்வ
    0.37
    чия
    0.37
    tr
    0.37
    Activations Density 0.000%

    No Known Activations