© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56900
    Prev
    Next
    INDEX
    Explanations

    credit rating agencies Moody's

    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_11_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
     occurring
    0.52
    ман
    0.52
     multitudes
    0.50
    ⵄ
    0.50
    Votes
    0.48
    ontology
    0.48
    マン
    0.47
     spiking
    0.47
    ራት
    0.47
    wallet
    0.46
    POSITIVE LOGITS
    দ্বীপ
    0.55
     Independence
    0.52
     gleiche
    0.50
     Independ
    0.49
     engl
    0.48
     -*-
    0.48
    诬
    0.48
     Uniwers
    0.47
     `=`,
    0.47
     Plains
    0.47
    Activations Density 0.001%

    No Known Activations