© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17981
    Prev
    Next
    INDEX
    Explanations

    Employer Identification Number

    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_34_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
     script
    0.46
     scripts
    0.46
     நூ
    0.46
     स्क्रिप्ट
    0.45
     Scripts
    0.45
     childrens
    0.42
     scripting
    0.39
    ꜰ
    0.39
    Script
    0.38
    SCRIPT
    0.37
    POSITIVE LOGITS
     registered
    0.55
     зарегистри
    0.54
    Registered
    0.53
     Enroll
    0.53
     enroll
    0.52
    registered
    0.52
    注册
    0.52
     Registered
    0.52
     регистра
    0.52
    号码
    0.51
    Activations Density 0.043%

    No Known Activations