Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 9281
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    ation
    3.55
    ATION
    2.22
    た
    1.77
    ние
    1.55
    ेशन
    1.19
    вання
    1.09
    ment
    1.08
    ung
    1.04
    ています
    1.02
    ление
    0.88
    POSITIVE LOGITS
     pleases
    0.69
     Hepburn
    0.61
    iędzy
    0.60
    ionized
    0.59
     Versicher
    0.59
    ங்களை
    0.58
    পৌ
    0.58
    鯰
    0.57
     보험
    0.57
    LAMP
    0.56
    Activations Density 0.410%

    No Known Activations