© 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. 166973
    Prev
    Next
    INDEX
    Explanations

    email validation regex

    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
     forced
    0.34
    CHAT
    0.33
     starve
    0.32
    forced
    0.31
     soaked
    0.31
     Trek
    0.30
    Truthy
    0.30
    №
    0.30
     kDa
    0.30
     Forced
    0.30
    POSITIVE LOGITS
     querido
    0.39
     kaas
    0.36
     samod
    0.36
     Administrator
    0.34
     candidat
    0.34
     পর্যবেক্ষণ
    0.34
    Administrator
    0.33
    设计
    0.33
     设计
    0.33
     criado
    0.32
    Activations Density 0.002%

    No Known Activations