© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9245
    Prev
    Next
    INDEX
    Explanations

    text describing regulatory bodies like the Competition and Markets Authority

    oai_token-act-pair · gemini-2.0-flash

    the/US

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Red
    -0.46
    ched
    -0.45
     gynhyrchwyd
    -0.45
     pulled
    -0.44
    jad
    -0.44
    zman
    -0.44
    ској
    -0.44
    Red
    -0.44
     فريبيس
    -0.43
     Ker
    -0.43
    POSITIVE LOGITS
    featureID
    0.74
     CWE
    0.65
    URLConnection
    0.63
    ngrx
    0.63
    fromnode
    0.61
    baomidou
    0.60
    ThroughAttribute
    0.60
     Paglinawan
    0.59
     wireType
    0.58
    sizeCache
    0.58
    Activations Density 6.706%

    No Known Activations