© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129888
    Prev
    Next
    INDEX
    Explanations

    horrific, pathetique, injuries

    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_6_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
    ре
    1.02
    ри
    1.01
    ل
    1.00
     or
    0.98
    ικ
    0.98
    ться
    0.98
     ऑन
    0.98
    ens
    0.97
    orElse
    0.96
    тэй
    0.95
    POSITIVE LOGITS
    in
    1.40
    .
    1.34
    ।
    1.01
    i
    1.00
    ]
    0.96
    。
    0.95
    *
    0.94
     في
    0.93
    י
    0.89
    他
    0.85
    Activations Density 0.000%

    No Known Activations