© 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. 6691
    Prev
    Next
    INDEX
    Explanations

    words beginning with "un" or containing "re" or "er".

    oai_token-act-pair · gemini-2.0-flash

    unt/und

    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
    Ĭ
    -0.66
     <<<<<<<<<<<<<<
    -0.65
     MOP
    -0.60
    InitVars
    -0.60
    VIAF
    -0.59
    AnchorStyles
    -0.59
     Trist
    -0.59
    ьажоргаш
    -0.58
    UnsafeEnabled
    -0.57
    ThroughAttribute
    -0.57
    POSITIVE LOGITS
     nuages
    0.71
     bénéfices
    0.68
     supérieures
    0.66
     blessés
    0.64
     supérieurs
    0.62
     âgées
    0.60
     prisonniers
    0.60
    setupUi
    0.59
     émotions
    0.58
    behaved
    0.57
    Activations Density 6.043%

    No Known Activations