© 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. 69
    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
    .[/
    0.19
    .​​
    0.18
    ပါတယ်။
    0.17
    ологи
    0.16
    ipotent
    0.16
    .
    0.15
     jederzeit
    0.15
    hæng
    0.15
     または
    0.15
     مدد
    0.15
    POSITIVE LOGITS
     S
    0.16
    V
    0.16
     A
    0.15
    S
    0.15
    A
    0.15
    开
    0.15
    K
    0.14
     fleurs
    0.14
    M
    0.14
    ouverture
    0.14
    Activations Density 0.426%

    No Known Activations