© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9837
    Prev
    Next
    INDEX
    Explanations

    presumption of innocence / deemed rent / safe harbor

    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_13_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
     ocean
    0.59
     constraints
    0.59
    0.58
     slicing
    0.56
     volcano
    0.55
     confess
    0.55
     excursions
    0.54
     s
    0.54
     avent
    0.54
     aspen
    0.53
    POSITIVE LOGITS
    а
    0.59
    abhut
    0.58
    cord
    0.57
    وج
    0.56
    𝗶
    0.55
     Букмекерская
    0.55
    Methylsulfanyl
    0.55
    챠
    0.55
    ರ್
    0.54
    bootstrap
    0.54
    Activations Density 0.023%

    No Known Activations