© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 235360
    Prev
    Next
    INDEX
    Explanations

    w czym

    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_32_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
    <unused39>
    0.41
     премии
    0.37
     worlds
    0.37
    ன்ப
    0.36
    essa
    0.36
    oucher
    0.36
    🏗
    0.36
    ceptions
    0.36
    鯵
    0.36
    ថ្ង
    0.36
    POSITIVE LOGITS
     addTo
    0.38
     insulted
    0.37
     arousal
    0.37
    mts
    0.36
    밈
    0.34
    叄
    0.34
    搬
    0.33
     streak
    0.33
     impulses
    0.33
     impulse
    0.33
    Activations Density 0.000%

    No Known Activations