© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89712
    Prev
    Next
    INDEX
    Explanations

    alphanumeric sequences

    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_11_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
     provide
    0.11
     однако
    0.11
     обратиться
    0.10
     તે
    0.10
     गह
    0.10
     の
    0.10
     созда
    0.10
    ૩
    0.10
     он
    0.10
     نصف
    0.10
    POSITIVE LOGITS
    갯
    0.11
    Ч
    0.11
     Pix
    0.10
    d
    0.10
    ᱦ
    0.10
    잉
    0.10
    ረስ
    0.10
    FLD
    0.10
    ст
    0.10
    g
    0.09
    Activations Density 0.007%

    No Known Activations