© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35313
    Prev
    Next
    INDEX
    Explanations

    big decisions and new chapters

    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
     lag
    0.36
     uncommon
    0.36
    சூ
    0.35
     perse
    0.35
     saves
    0.35
    agno
    0.35
     enrich
    0.34
    笔
    0.33
    ᄋ
    0.33
    颀
    0.33
    POSITIVE LOGITS
    transitions
    0.39
    transition
    0.39
    Trigger
    0.38
     memulai
    0.38
     nostalg
    0.37
    Transitions
    0.37
    taskList
    0.37
     transition
    0.37
     compito
    0.36
     congratulate
    0.36
    Activations Density 0.068%

    No Known Activations