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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5462
    Prev
    Next
    INDEX
    Explanations

    cloud functions

    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
    ました
    1.11
     छुट्ट
    0.90
    ю
    0.87
    \,\
    0.84
    =(\
    0.83
    awesome
    0.83
    javax
    0.82
    רה
    0.82
    $:
    0.82
    您可以
    0.81
    POSITIVE LOGITS
     vencer
    1.11
     gestaltet
    1.06
     strani
    1.06
     buildFor
    1.04
    delimiter
    1.02
     इंस्टॉल
    1.01
    adeso
    0.99
     präsent
    0.98
     quoique
    0.98
    শিরোনাম
    0.98
    Activations Density 0.001%

    No Known Activations