© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139020
    Prev
    Next
    INDEX
    Explanations

    LCD, e-ink, liquid crystals

    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_12_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
     ITA
    0.52
    رض
    0.50
    ревно
    0.50
     मीरा
    0.47
    日閲覧
    0.47
    }]$
    0.47
    ोदय
    0.46
     ALSO
    0.45
    ويم
    0.45
     DOES
    0.45
    POSITIVE LOGITS
    par
    0.53
    arr
    0.50
     pascal
    0.50
    ik
    0.48
     amb
    0.48
    val
    0.47
    obj
    0.47
    ಲಿಲ್ಲ
    0.47
    any
    0.47
    <0x0D>
    0.47
    Activations Density 0.007%

    No Known Activations