© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8608
    Prev
    Next
    INDEX
    Explanations

    a variety of mostly technical terms.

    oai_token-act-pair · gemini-2.0-flash

    Scientific/technical descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     starting
    -1.15
    starting
    -1.12
    Starting
    -1.10
     Starting
    -1.10
     STARTING
    -1.04
     turning
    -0.97
     ending
    -0.96
     coming
    -0.94
     arriving
    -0.94
     opening
    -0.93
    POSITIVE LOGITS
    COUVER
    0.68
     monitoring
    0.67
     accounting
    0.65
    
    0.64
    MethodManager
    0.62
    monitoring
    0.60
    accounting
    0.60
    الدراسه
    0.60
     playing
    0.58
     informée
    0.57
    Activations Density 6.265%

    No Known Activations