© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 13084
    Prev
    Next
    INDEX
    Explanations

    instances of connecting with something

    oai_token-act-pair · gemini-2.0-flash

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    RectangleBorder
    -0.81
     betweenstory
    -0.75
    AnchorTagHelper
    -0.67
    sidemargin
    -0.66
    الحياه
    -0.65
     Majefty
    -0.64
     Theſe
    -0.63
     iſt
    -0.63
     TÉCN
    -0.62
    AndEndTag
    -0.62
    POSITIVE LOGITS
    lobal
    0.52
     session
    0.49
    commutative
    0.48
    tellation
    0.47
     situational
    0.47
     attendre
    0.47
     पहुंच
    0.46
     mar
    0.46
    insics
    0.46
     fo
    0.45
    Activations Density 5.297%

    No Known Activations