© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 47-GEMMASCOPE-2-TRANSCODER-262K
    4. 216810
    Prev
    Next
    INDEX
    Explanations

    passing

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
    ises
    0.41
     upward
    0.41
     aj
    0.41
    osas
    0.40
    ISES
    0.38
    PRS
    0.38
    조
    0.38
    arsa
    0.37
    aji
    0.37
    cs
    0.37
    POSITIVE LOGITS
    Miss
    0.41
     வைத்திருக்க
    0.41
    Ⲟ
    0.40
    筋肉
    0.38
     fancied
    0.37
    快
    0.37
     poč
    0.37
    disco
    0.37
    캐
    0.36
    criptor
    0.36
    Activations Density 0.000%

    No Known Activations