© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133992
    Prev
    Next
    INDEX
    Explanations

    dizzying

    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_6_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
    в
    1.59
    м
    1.48
    по
    1.38
    па
    1.37
    ра
    1.34
    ни
    1.28
    ве
    1.28
    и
    1.27
    о
    1.26
    у
    1.25
    POSITIVE LOGITS
    )
    1.05
     for
    0.96
    }
    0.93
    Norm
    0.90
    Mut
    0.88
    Mere
    0.87
     disse
    0.86
    tus
    0.86
    Mer
    0.83
     temer
    0.83
    Activations Density 0.000%

    No Known Activations