© 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
    2. Gemma-3-4B-IT
    3. 12-GEMMASCOPE-2-TRANSCODER-16K
    4. 62
    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_12_width_16k_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
     또한
    0.24
    또한
    0.24
    itesse
    0.20
    meier
    0.20
    ě
    0.19
     بالإضافة
    0.19
    மையும்
    0.18
    atrice
    0.18
     최대
    0.18
    прежнему
    0.18
    POSITIVE LOGITS
    还不
    0.20
     corrigir
    0.18
     prophe
    0.17
    <unused13>
    0.17
     teori
    0.17
     confused
    0.17
     Roth
    0.17
     gaf
    0.17
     ഗു
    0.17
     khawatir
    0.17
    Activations Density 0.284%

    No Known Activations