© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6102
    Prev
    Next
    INDEX
    Explanations

    C# code statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    
    2.28
    
    2.25
    _.
    2.24
     indors
    2.22
    getJSONObject
    2.05
    ಬ್ಬಿಣ
    2.02
    upcoming
    2.01
    寐
    2.00
    unsigned
    1.95
    ദ്ധതി
    1.93
    POSITIVE LOGITS
    ر
    2.97
    და
    2.24
    िंग
    2.23
    いった
    2.22
    вим
    2.19
    ldap
    2.19
    יות
    2.17
     zwar
    2.16
    \)
    2.15
    鵡
    2.13
    Activations Density 0.001%

    No Known Activations