© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12066
    Prev
    Next
    INDEX
    Explanations

    words related to engineering and materials science

    oai_token-act-pair · gemini-2.0-flash

    Code and technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jap
    -0.57
     technique
    -0.54
     Technique
    -0.54
     Component
    -0.54
     components
    -0.53
     quantities
    -0.53
     quantity
    -0.53
    angle
    -0.53
     household
    -0.53
     Components
    -0.52
    POSITIVE LOGITS
    RUnlock
    0.71
     GenerationType
    0.64
    numerusform
    0.61
    OGND
    0.56
    MLLoader
    0.56
     HasFactory
    0.56
    Obrázky
    0.54
     contextLoads
    0.53
     Signalez
    0.53
    epiece
    0.52
    Activations Density 2.690%

    No Known Activations