© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132570
    Prev
    Next
    INDEX
    Explanations

    police report

    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
    IS
    0.82
    ن
    0.81
    น
    0.80
    น้อง
    0.80
    ও
    0.80
    EN
    0.78
    IN
    0.76
    LE
    0.76
     statesman
    0.75
    AR
    0.74
    POSITIVE LOGITS
    y
    1.13
    b
    0.99
    ut
    0.98
    i
    0.87
    c
    0.82
    op
    0.79
    ي
    0.78
    e
    0.74
    ból
    0.74
    j
    0.74
    Activations Density 0.007%

    No Known Activations