© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110635
    Prev
    Next
    INDEX
    Explanations

    illicit activity

    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_2_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
    های
    1.13
    ться
    1.05
    ियां
    1.03
     (
    1.02
    سی
    0.98
    یشه
    0.96
    ਰ
    0.89
    لی
    0.89
    یت
    0.88
    یس
    0.87
    POSITIVE LOGITS
    <0x0D>
    1.27
    1.17
    يد
    1.13
    2
    1.13
    </h3>
    1.08
    EE
    1.08
    T
    1.05
    </i>
    1.03
    O
    1.03
    一
    1.03
    Activations Density 0.000%

    No Known Activations