© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120960
    Prev
    Next
    INDEX
    Explanations

    private and public access modifiers

    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
     يصير
    0.38
    apatkan
    0.38
    anjan
    0.37
     زيد
    0.36
     enroll
    0.36
    ãng
    0.35
     वर्चुअल
    0.35
    +(-
    0.35
    ilfe
    0.35
     методы
    0.35
    POSITIVE LOGITS
     Chi
    0.38
     Beige
    0.35
     дизайна
    0.35
    Sliced
    0.35
     Undoubtedly
    0.34
     Chia
    0.34
     douceur
    0.33
     लिहाज
    0.33
     Bang
    0.33
     réessayer
    0.33
    Activations Density 0.000%

    No Known Activations