© 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. 139523
    Prev
    Next
    INDEX
    Explanations

    giant things

    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
    ’
    0.74
    интере
    0.59
     devant
    0.57
    '
    0.57
    et
    0.53
     financiera
    0.53
     cargar
    0.52
     cuales
    0.52
     bares
    0.51
     enormes
    0.51
    POSITIVE LOGITS
    Farmers
    0.63
     ہیں
    0.61
    6
    0.59
    </h2>
    0.58
     زیادہ
    0.57
    𝗢
    0.56
    cient
    0.56
     चिकित्सा
    0.55
     націона
    0.55
     সুরক্ষা
    0.55
    Activations Density 0.001%

    No Known Activations