© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199608
    Prev
    Next
    INDEX
    Explanations

    longest common subsequence

    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
    чите
    0.53
    чва
    0.47
    ட்
    0.47
    قلال
    0.46
    IGNORE
    0.46
     }}$.
    0.45
    WS
    0.45
    Seb
    0.45
    CTOR
    0.44
     general
    0.44
    POSITIVE LOGITS
    ？”
    0.66
    ？
    0.62
    ？）
    0.53
    藁
    0.53
     എ
    0.53
    。”
    0.53
     Jahren
    0.52
     เอ
    0.52
    గం
    0.52
    পাত্র
    0.51
    Activations Density 0.002%

    No Known Activations