© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 221023
    Prev
    Next
    INDEX
    Explanations

    dollar sign and specific code/commands

    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
     coveredmethods
    0.41
     kidneys
    0.41
    MCU
    0.40
     neph
    0.39
    dl
    0.38
     ron
    0.38
    大臣
    0.38
    ຟ
    0.38
     dandruff
    0.37
    ifan
    0.37
    POSITIVE LOGITS
     dollar
    0.38
     '$
    0.38
     `$
    0.37
    เงิน
    0.36
     Объ
    0.36
     पैसे
    0.36
     Lamborghini
    0.36
     Dollar
    0.35
     ($
    0.35
     menjelaskan
    0.34
    Activations Density 0.000%

    No Known Activations