© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4295
    Prev
    Next
    INDEX
    Explanations

    How's your going

    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_40_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
    }}$-
    0.36
    ӥ
    0.35
    wiata
    0.34
    Nell
    0.34
    ACTIVITY
    0.33
     beat
    0.33
    ('-
    0.31
    isine
    0.31
    摆
    0.30
     activity
    0.30
    POSITIVE LOGITS
     Klik
    0.38
     clicking
    0.37
    nić
    0.36
     காவல்துற
    0.36
     ቀለም
    0.36
     साहित्यिक
    0.35
     infrastrukt
    0.35
     Schumann
    0.35
     policial
    0.35
    昃
    0.34
    Activations Density 0.006%

    No Known Activations