© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34934
    Prev
    Next
    INDEX
    Explanations

    model definition

    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_31_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
     мем
    0.37
    𝚏
    0.37
    ట్‌లో
    0.35
    هَا
    0.35
     कमेंट
    0.33
    帧
    0.33
    甲方
    0.33
     Sở
    0.33
    きゃ
    0.33
    FAs
    0.33
    POSITIVE LOGITS
    Decode
    0.38
    istische
    0.37
    ardia
    0.37
     nug
    0.37
    отно
    0.37
    Logic
    0.36
    Par
    0.36
    Ret
    0.36
    iation
    0.36
    Connect
    0.36
    Activations Density 0.001%

    No Known Activations