© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87146
    Prev
    Next
    INDEX
    Explanations

    hardware, machinery, operator, health

    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_3_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
    ä
    1.27
    ر
    0.97
    ли
    0.95
    ]
    0.94
    K
    0.86
    }
    0.84
    )
    0.84
    N
    0.82
     It
    0.81
    د
    0.76
    POSITIVE LOGITS
    𝓼
    0.82
    ların
    0.78
    lz
    0.73
    🧧
    0.73
    AOrdenar
    0.71
     venant
    0.71
    a
    0.71
    ları
    0.70
    guan
    0.70
    ARE
    0.70
    Activations Density 0.018%

    No Known Activations