© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 87553
    Prev
    Next
    INDEX
    Explanations

    think before questions

    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_23_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
     kuz
    0.24
    ]_
    0.23
    ys
    0.22
     বহ
    0.22
    hotels
    0.22
    тов
    0.22
     Defenders
    0.22
    img
    0.21
     durability
    0.21
     usd
    0.21
    POSITIVE LOGITS
    विज्ञान
    0.25
     такими
    0.24
    AGENT
    0.24
     такі
    0.23
     அமைந்துள்ள
    0.23
    সঙ্ঘ
    0.23
    ➩
    0.22
     गर्भ
    0.22
     чове
    0.22
     গজ
    0.22
    Activations Density 0.002%

    No Known Activations