© 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. 16091
    Prev
    Next
    INDEX
    Explanations

    sentences describing events happening during some period of time

    oai_token-act-pair · gemini-2.0-flash

    During

    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
    脚注の使い方
    -0.69
     préc
    -0.66
     supérieures
    -0.61
     actuels
    -0.59
     privées
    -0.57
     venons
    -0.54
     recepción
    -0.53
    جغرافيا
    -0.52
    ederen
    -0.51
    aroos
    -0.51
    POSITIVE LOGITS
     houſe
    0.96
     pleaſure
    0.90
     himſelf
    0.86
     purpoſe
    0.86
     reaſon
    0.84
     perſon
    0.83
     ſtand
    0.83
     itſelf
    0.82
     Jefus
    0.82
     poffe
    0.82
    Activations Density 4.696%

    No Known Activations