© 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. 3000
    Prev
    Next
    INDEX
    Explanations

    words related to personal preferences and customization

    oai_token-act-pair · gemini-2.0-flash

    Meeting customer needs

    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
     purpoſe
    -0.84
     myſelf
    -0.81
     Chriftian
    -0.80
     Majefty
    -0.80
    URLException
    -0.79
     pleaſure
    -0.77
     leaſt
    -0.76
     Efq
    -0.75
     itſelf
    -0.75
     houſe
    -0.73
    POSITIVE LOGITS
     des
    0.42
    Barre
    0.41
     comme
    0.40
     wants
    0.39
    ächlich
    0.37
    akteur
    0.36
     file
    0.36
    ritter
    0.35
    กุ
    0.35
     needs
    0.35
    Activations Density 2.102%

    No Known Activations