© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213521
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_5_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
    }
    1.51
     the
    1.47
    )
    1.44
     of
    1.40
    {
    1.34
     an
    1.33
    ]
    1.33
     by
    1.31
     to
    1.17
     from
    1.17
    POSITIVE LOGITS
    지
    1.13
    1.09
    궪
    1.02
    ра
    1.00
    ли
    0.98
    кт
    0.96
    ль
    0.95
    지와
    0.95
    j
    0.94
    ની
    0.93
    Activations Density 0.000%

    No Known Activations