© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12531
    Prev
    Next
    INDEX
    Explanations

    mentions of computer servers

    oai_token-act-pair · gemini-2.0-flash

    server

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    erapeu
    -0.85
    <bos>
    -0.75
    InjectAttribute
    -0.72
    IsMutable
    -0.70
    tisol
    -0.70
    Carriera
    -0.69
    lexia
    -0.68
     ocu
    -0.68
    курен
    -0.65
     frizz
    -0.64
    POSITIVE LOGITS
    .$.
    0.64
    — 
    0.61
    >--}}
    0.61
    ()]
    0.58
    =");
    0.57
    enumii
    0.55
    OTO
    0.55
    =")
    0.55
     roaring
    0.54
    )))
    0.54
    Activations Density 1.602%

    No Known Activations