© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45367
    Prev
    Next
    INDEX
    Explanations

    realize how or thinking about

    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_22_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
    cooked
    0.24
     shitty
    0.24
    ➧
    0.24
     crappy
    0.23
    షా
    0.23
     Clarkson
    0.22
     McPherson
    0.22
    出来ない
    0.22
    formatted
    0.21
    駿
    0.21
    POSITIVE LOGITS
    حث
    0.22
     elders
    0.21
     verw
    0.20
     selectTable
    0.20
     fratern
    0.20
    र्ती
    0.20
    correo
    0.20
    ቈ
    0.20
    总结
    0.20
     Кор
    0.20
    Activations Density 0.003%

    No Known Activations