© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91008
    Prev
    Next
    INDEX
    Explanations

    CTF competitions and dysfunction

    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
    k
    0.86
    và
    0.81
    w
    0.76
    ký
    0.76
    kova
    0.71
    körper
    0.70
    肦
    0.70
    te
    0.69
    鸴
    0.69
    ne
    0.68
    POSITIVE LOGITS
    ’
    1.37
    )
    0.96
    )’
    0.94
    ה
    0.93
    ]
    0.86
    ))
    0.84
    ע
    0.83
    다
    0.79
     persiapan
    0.78
    '
    0.78
    Activations Density 0.000%

    No Known Activations