© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108444
    Prev
    Next
    INDEX
    Explanations

    book

    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_2_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
    يد
    1.46
    ла
    1.32
    <0x80>
    1.21
    ى
    1.16
    ير
    1.13
    ar
    1.09
    ర్
    1.09
     baloncesto
    1.06
    يق
    1.05
    ো
    1.05
    POSITIVE LOGITS
     synthes
    1.18
     hypothes
    1.05
    ни
    1.02
    ların
    1.02
    変
    0.98
     तरह
    0.98
     decentral
    0.97
    dimethyl
    0.96
    ssä
    0.96
    انی
    0.95
    Activations Density 0.004%

    No Known Activations