© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 260250
    Prev
    Next
    INDEX
    Explanations

    Burton Malkiel

    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_10_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
     Sito
    0.36
     tiếng
    0.36
    Flight
    0.33
     적극
    0.33
     یہاں
    0.33
    ходе
    0.33
     Batterie
    0.32
    럇
    0.32
    Characteristics
    0.32
     ধান
    0.31
    POSITIVE LOGITS
     över
    0.46
     wastewater
    0.41
     zoveel
    0.39
     jewelry
    0.39
     finest
    0.39
     stov
    0.39
     prompted
    0.39
    ओसी
    0.39
    ozems
    0.38
     thousands
    0.38
    Activations Density 0.000%

    No Known Activations