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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 244739
    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_11_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
    үндө
    1.27
     источник
    1.25
     несмотря
    1.15
    irán
    1.13
     只
    1.12
     hitch
    1.12
     источники
    1.10
     Participating
    1.09
     بحيث
    1.08
    osť
    1.07
    POSITIVE LOGITS
     unge
    1.19
    currentPlayer
    1.17
    sos
    1.15
    Neue
    1.13
    Masukkan
    1.07
     Sachen
    1.07
    ए
    1.05
     gripped
    1.05
    רות
    1.04
    ल्डेन
    1.03
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.