© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45645
    Prev
    Next
    INDEX
    Explanations

    file systems (FAT, NTFS)

    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_13_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
     Т
    0.43
     т
    0.42
     зат
    0.41
     sharper
    0.41
     anatomical
    0.40
     eti
    0.40
     девушка
    0.39
     պ
    0.37
     જરૂરી
    0.37
     รูป
    0.37
    POSITIVE LOGITS
     Tyne
    0.47
     söyl
    0.43
    Alright
    0.43
    หยุด
    0.43
    완
    0.42
    </em>
    0.41
     Norton
    0.41
     Spence
    0.41
    FullPath
    0.41
    όν
    0.41
    Activations Density 0.025%

    No Known Activations