© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90054
    Prev
    Next
    INDEX
    Explanations

    next door

    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_11_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
     (“
    0.58
     reflects
    0.58
     criticized
    0.54
    ..<
    0.54
    𝗿
    0.54
    .”
    0.53
     (‘
    0.53
     갔
    0.53
    𝚑
    0.53
     ("
    0.52
    POSITIVE LOGITS
    0.72
     Osm
    0.61
    पर
    0.59
    ơn
    0.58
     AsyncStorage
    0.55
    نت
    0.55
    yl
    0.55
    قل
    0.54
     Pfizer
    0.54
    ने
    0.53
    Activations Density 0.000%

    No Known Activations