© 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. 8505
    Prev
    Next
    INDEX
    Explanations

    words in a Slavic language related to privacy and acceptance of terms

    oai_token-act-pair · gemini-2.0-flash

    Punctuation

    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
     Efq
    -1.36
     itſelf
    -1.29
    تقاوى
    -1.22
     myſelf
    -1.22
     <>",
    -1.20
    ſelves
    -1.19
    ſelf
    -1.17
     pleaſure
    -1.15
    EndGlobalSection
    -1.13
    nefs
    -1.13
    POSITIVE LOGITS
     
    0.79
    -
    0.71
     (
    0.69
     N
    0.68
    <eos>
    0.64
    ↵
    0.63
     Y
    0.62
    :
    0.61
    ↵↵
    0.61
     -
    0.60
    Activations Density 0.347%

    No Known Activations