© 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. 49226
    Prev
    Next
    INDEX
    Explanations

    as a Service

    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
    nivel
    0.36
     Mank
    0.36
     değil
    0.36
    亣
    0.35
     bach
    0.35
    ریت
    0.34
     recycle
    0.34
     menú
    0.34
    哣
    0.34
    MenuList
    0.34
    POSITIVE LOGITS
    otives
    0.39
    rones
    0.38
    shi
    0.38
    ini
    0.37
    precise
    0.37
    ോള
    0.35
    hacking
    0.34
    plic
    0.34
     adhering
    0.34
     भ्र
    0.34
    Activations Density 0.005%

    No Known Activations