© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10507
    Prev
    Next
    INDEX
    Explanations

    words related to git commands

    oai_token-act-pair · gemini-2.0-flash

    git

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     pic
    -0.51
    photobucket
    -0.48
     seized
    -0.48
     Open
    -0.45
    Seller
    -0.44
     imperio
    -0.44
    Open
    -0.44
    官
    -0.44
    Code
    -0.44
     open
    -0.44
    POSITIVE LOGITS
    principalColumn
    0.80
    enumi
    0.78
     الحره
    0.77
    DockStyle
    0.74
     myſelf
    0.72
    
    0.72
     Reſ
    0.71
     Eſ
    0.68
     Jefus
    0.68
    TagHelper
    0.66
    Activations Density 1.114%

    No Known Activations