© 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. 16176
    Prev
    Next
    INDEX
    Explanations

    mentions of wood-burning heat sources

    oai_token-act-pair · gemini-2.0-flash

    fire and heating

    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
    StructEnd
    -1.20
     CreateTagHelper
    -0.98
    Geplaatst
    -0.93
     beginnetje
    -0.91
     pinulongan
    -0.90
     Савезне
    -0.88
    principalTable
    -0.88
     mergeFrom
    -0.87
    AccessorTable
    -0.85
    DeleteBehavior
    -0.85
    POSITIVE LOGITS
     paš
    0.46
     Drapeau
    0.45
     Brethren
    0.45
     ball
    0.43
    st
    0.41
     fint
    0.40
    球
    0.39
    架
    0.39
     community
    0.38
    community
    0.38
    Activations Density 1.154%

    No Known Activations