© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 16207
    Prev
    Next
    INDEX
    Explanations

    negative expressions

    oai_token-act-pair · gemini-2.0-flash

    no

    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
     Really
    -0.64
     really
    -0.63
     yet
    -0.62
    Really
    -0.60
     resourceCulture
    -0.60
    matter
    -0.59
    enumi
    -0.59
    RegistryLite
    -0.59
     Yet
    -0.59
    CodedInputStream
    -0.57
    POSITIVE LOGITS
    Obrázky
    0.55
     NPA
    0.47
    Personensuche
    0.47
     warlock
    0.46
    Étymologie
    0.46
     UCB
    0.44
     tassels
    0.44
    šanās
    0.43
    atellite
    0.43
    plona
    0.42
    Activations Density 3.563%

    No Known Activations