© 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. 197616
    Prev
    Next
    INDEX
    Explanations

    long form arguments

    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
     hardening
    0.39
     خار
    0.36
     mă
    0.36
     Alic
    0.34
     culminating
    0.34
     ا
    0.34
     ফর
    0.34
     ảo
    0.34
     weiter
    0.33
     tiêu
    0.33
    POSITIVE LOGITS
    nsan
    0.40
    стера
    0.39
    Needless
    0.39
    룔
    0.38
    acci
    0.38
    সংস্কার
    0.38
    Stephen
    0.38
     एक्सपीरियंस
    0.38
    жет
    0.37
     prejudiced
    0.37
    Activations Density 0.000%

    No Known Activations