Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 6956
    Prev
    Next
    INDEX
    Explanations

    sentences that express a possibility, plan, or intention for the future and/or tension.

    oai_token-act-pair · gemini-2.0-flash

    remaining

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Савезне
    -0.71
     NSCoder
    -0.63
    RegistryLite
    -0.52
    Спољашње
    -0.50
    kloped
    -0.50
    CompleteListener
    -0.49
    ็จ
    -0.48
    AddTagHelper
    -0.47
     دیکھیے
    -0.47
    êmios
    -0.46
    POSITIVE LOGITS
     remain
    1.80
     remained
    1.76
     stays
    1.69
     stayed
    1.68
     stay
    1.68
    stay
    1.63
    remain
    1.61
     remains
    1.60
     staying
    1.59
     Stay
    1.59
    Activations Density 2.698%

    No Known Activations