© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 195326
    Prev
    Next
    INDEX
    Explanations

    legal judgments and convictions

    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_27_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
    笥
    0.40
     Tempest
    0.39
    凳
    0.39
     dimensiones
    0.36
    􀂃
    0.35
    蓴
    0.35
     Developments
    0.35
     Neutron
    0.35
    dien
    0.34
     neut
    0.34
    POSITIVE LOGITS
     FETCH
    0.39
     collectible
    0.36
     encoded
    0.35
     qubit
    0.35
     lookup
    0.35
    釀
    0.35
     timeline
    0.35
     curated
    0.34
     enticing
    0.34
    Fetch
    0.34
    Activations Density 0.000%

    No Known Activations