© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62529
    Prev
    Next
    INDEX
    Explanations

    malignoma-, parenchyma-, lagomorpha-

    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_2_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
    )
    1.99
    }
    1.72
    ]
    1.58
    ۔
    1.52
     I
    1.48
    是
    1.46
    。
    1.44
    ።
    1.30
    д
    1.23
    ।
    1.23
    POSITIVE LOGITS
    ன்
    1.24
    ل
    1.06
    $)$.
    0.99
    fie
    0.98
    t
    0.96
    ى
    0.94
    bner
    0.93
    fda
    0.93
    ان
    0.89
    rary
    0.89
    Activations Density 0.006%

    No Known Activations