© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260045
    Prev
    Next
    INDEX
    Explanations

    seeking escape or something new

    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_22_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
     vmax
    0.52
    ம்மா
    0.46
     lás
    0.44
     longitudine
    0.42
    ভ
    0.42
     vst
    0.41
    規制
    0.40
     pedibus
    0.39
     ۱۹
    0.39
     ngram
    0.39
    POSITIVE LOGITS
    ieux
    0.46
     Осо
    0.44
    oin
    0.41
    ospital
    0.41
    ügen
    0.40
    g
    0.40
    的新
    0.39
    cuits
    0.39
    tható
    0.39
     মধ্যকার
    0.38
    Activations Density 0.002%

    No Known Activations