© 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
    3. Gemma-3-27B-IT
    5. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 209289
    Prev
    Next
    INDEX
    Explanations

    Sky Islands

    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_19_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
    이버
    0.52
    ᄇ
    0.48
    ন্ত্র
    0.47
    servername
    0.44
     beforePath
    0.43
     subtracted
    0.42
     soff
    0.41
    ᅳ
    0.40
    곰
    0.40
    ngModel
    0.39
    POSITIVE LOGITS
     islands
    0.43
    éc
    0.42
     mon
    0.42
     sea
    0.42
     Sea
    0.42
    ולנדי
    0.42
    ဟုတ်
    0.41
     island
    0.41
     RAID
    0.41
    sea
    0.41
    Activations Density 0.000%

    No Known Activations