© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18643
    Prev
    Next
    INDEX
    Explanations

    criminal charges and sentences

    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_40_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
     Seo
    0.40
     Juliet
    0.38
     রোগের
    0.38
    ადგენ
    0.38
     Schulen
    0.37
    软
    0.37
     vit
    0.37
    锁
    0.36
     rub
    0.36
    ᔨ
    0.36
    POSITIVE LOGITS
     sente
    0.44
    Judgment
    0.41
     judgment
    0.40
     SEND
    0.39
    judgment
    0.39
    Placement
    0.38
     DMD
    0.38
    SEN
    0.37
    SEND
    0.37
     integrative
    0.37
    Activations Density 0.018%

    No Known Activations