© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207480
    Prev
    Next
    INDEX
    Explanations

    legal conduct, ethics, rules, capture

    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_20_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
    cnico
    0.44
    ibility
    0.44
     Jefferson
    0.43
    चुअल
    0.43
     rhetorical
    0.42
     Statutes
    0.41
    賴
    0.41
     Ze
    0.41
    ্রান্ত
    0.41
     Hai
    0.41
    POSITIVE LOGITS
    珩
    0.45
    )<-
    0.44
    干净
    0.43
    酰
    0.42
     clean
    0.42
     вклю
    0.42
    shown
    0.40
    合格
    0.40
    นี
    0.40
    )].
    0.40
    Activations Density 0.000%

    No Known Activations