© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 15284
    Prev
    Next
    INDEX
    Explanations

    github.com import paths

    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_15_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
    ]
    0.59
    There
    0.53
    ف
    0.53
    ];
    0.52
    According
    0.51
     instante
    0.51
    encana
    0.48
    f
    0.48
    <0xE3>
    0.47
     Airways
    0.47
    POSITIVE LOGITS
     bits
    0.47
    蚩
    0.47
     pcs
    0.46
     dichlor
    0.46
    iku
    0.46
    নৈতিক
    0.46
    ње
    0.46
     টেব
    0.45
     ök
    0.45
    िलाई
    0.45
    Activations Density 0.004%

    No Known Activations