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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14905
    Prev
    Next
    INDEX
    Explanations

    conjunctions and related words indicating a sequence of steps or logic.

    oai_token-act-pair · gemini-2.0-flash

    conjunctions/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_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ,:);
    -0.89
    enumi
    -0.88
     BoxFit
    -0.83
    +#+#
    -0.81
    ]^{-
    -0.78
    AnimationsModule
    -0.75
     auffi
    -0.74
    __":
    
    -0.73
    DockStyle
    -0.72
    ^(@)
    -0.72
    POSITIVE LOGITS
     with
    1.64
    with
    1.30
     through
    1.28
     avec
    1.27
     dengan
    1.13
     by
    1.11
    through
    1.05
    With
    1.05
     mediante
    1.03
     With
    1.02
    Activations Density 2.285%

    No Known Activations