© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43026
    Prev
    Next
    INDEX
    Explanations

    hi-hats

    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
     Combs
    0.50
     bourgeois
    0.47
    รุ่น
    0.46
     preservatives
    0.45
     внутреннего
    0.44
    ⇉
    0.44
     combs
    0.44
     καλύτε
    0.43
     collim
    0.43
     capsid
    0.43
    POSITIVE LOGITS
    <0xA1>
    0.42
    <0x84>
    0.40
    ю
    0.38
    iku
    0.37
     so
    0.37
    textContent
    0.36
    рес
    0.36
    ربع
    0.36
     सिक्
    0.36
    φο
    0.35
    Activations Density 0.002%

    No Known Activations