© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43632
    Prev
    Next
    INDEX
    Explanations

    as Query | Application

    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_13_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
     पढ़कर
    0.48
     групи
    0.46
     зав
    0.44
    牞
    0.44
    ർട്ട
    0.43
    тех
    0.43
    textView
    0.43
     nChar
    0.43
    嫘
    0.43
     दिवंगत
    0.42
    POSITIVE LOGITS
    OKR
    0.47
    :
    0.46
    Hobbies
    0.42
     j
    0.42
     hábitos
    0.42
     l
    0.42
    
    0.41
    ()}')
    0.41
    ahana
    0.41
    }')
    0.40
    Activations Density 0.002%

    No Known Activations