© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87200
    Prev
    Next
    INDEX
    Explanations

    names and associated subsequent words

    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
    ي
    0.91
    '
    0.74
    Avec
    0.65
     sensitized
    0.63
    م
    0.61
    스를
    0.61
     ሽፋ
    0.60
     estadísticas
    0.60
    ttes
    0.59
    મ
    0.59
    POSITIVE LOGITS
    ATING
    0.76
    -
    0.64
    ]
    0.60
    یل
    0.57
    ography
    0.56
    लेंट
    0.56
    ATION
    0.56
     trope
    0.55
    ]}$.
    0.55
    $,
    0.54
    Activations Density 0.000%

    No Known Activations