© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52352
    Prev
    Next
    INDEX
    Explanations

    state and local laws

    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_31_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
    渍
    0.43
    songwriter
    0.41
     উইকেট
    0.40
    enderita
    0.39
    𒊕
    0.39
    सभा
    0.37
     aggiunto
    0.37
    的山
    0.36
    ála
    0.36
    )&
    0.36
    POSITIVE LOGITS
    幻
    0.45
    Arth
    0.42
     attempts
    0.39
    Jupiter
    0.38
     Palmer
    0.36
     validity
    0.36
    kali
    0.36
    Km
    0.36
     FACT
    0.36
     kilometer
    0.35
    Activations Density 0.001%

    No Known Activations