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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1029
    Prev
    Next
    INDEX
    Explanations

    statistics related to mean and standard error/deviation

    oai_token-act-pair · gemini-2.0-flash

    Standard error and deviation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    rylic
    -0.48
     gainera
    -0.48
    LookAnd
    -0.48
    ServletConfig
    -0.47
     count
    -0.44
    🇶
    -0.43
    Expose
    -0.42
    INAS
    -0.42
    diac
    -0.41
    SourceChecksum
    -0.41
    POSITIVE LOGITS
    tvguidetime
    0.82
     ✭✭
    0.67
    wiſe
    0.66
    MessageTagHelper
    0.65
    ſelves
    0.64
    帖最后由
    0.63
    ^(@)
    0.63
    клопе
    0.63
     myſelf
    0.62
    ſelf
    0.62
    Activations Density 2.226%

    No Known Activations