© 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. 9
    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
    1
    0.19
     probabilidad
    0.17
    你
    0.17
    9
    0.16
    7
    0.16
    6
    0.16
    ૧
    0.16
    5
    0.16
     две
    0.15
     грудня
    0.15
    POSITIVE LOGITS
     instill
    0.15
     instilled
    0.14
     facility
    0.14
    coating
    0.13
     sponsorships
    0.13
    iled
    0.13
    celer
    0.13
     feel
    0.13
     fellows
    0.13
     forms
    0.13
    Activations Density 0.598%

    No Known Activations