© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 178491
    Prev
    Next
    INDEX
    Explanations

    template/layout examples

    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_24_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
     realignment
    0.46
     स्मिथ
    0.46
    <unused34>
    0.46
    setConfig
    0.45
    λημα
    0.45
     बर्बाद
    0.44
    மாக
    0.44
    ﻊ
    0.44
     volte
    0.43
    גע
    0.43
    POSITIVE LOGITS
    م
    0.50
        
    0.46
     Physically
    0.46
    <0x0D>
    0.46
    对于
    0.46
    0.46
     cameras
    0.44
     Polymers
    0.44
     to
    0.44
    }}$,
    0.44
    Activations Density 0.000%

    No Known Activations