© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 164500
    Prev
    Next
    INDEX
    Explanations

    loop iterating with i or row

    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_31_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
    <0x9A>
    0.37
     pool
    0.37
    בה
    0.36
     забе
    0.36
     utt
    0.36
     Gaston
    0.35
     Nap
    0.35
     Denton
    0.34
    池
    0.34
     ABC
    0.34
    POSITIVE LOGITS
     Builds
    0.44
    䩕
    0.42
    又は
    0.42
     اڈوں
    0.41
     ἢ
    0.40
    하거나
    0.39
    చిన
    0.39
     Allowed
    0.39
    거나
    0.38
    Creates
    0.38
    Activations Density 0.003%

    No Known Activations