© 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. 53582
    Prev
    Next
    INDEX
    Explanations

    non-english characters and punctuation

    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
    ऐसे
    0.35
     দ্বন্দ্ব
    0.34
     situ
    0.33
    旛
    0.32
    艾
    0.32
    μος
    0.32
    alini
    0.32
    Droite
    0.32
     somme
    0.31
    Objectives
    0.31
    POSITIVE LOGITS
     colonized
    0.36
     tonight
    0.35
    滋
    0.34
    aranteed
    0.34
     вече
    0.34
    ("-"
    0.34
     рассе
    0.34
     kolon
    0.34
    korzyst
    0.33
    奔驰
    0.33
    Activations Density 0.000%

    No Known Activations