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. 14311
    Prev
    Next
    INDEX
    Explanations

    phrases related to exclusion, removal, or emotional disappointment

    oai_token-act-pair · gemini-2.0-flash

    removed

    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
    Into
    -0.65
     Into
    -0.58
     InputDecoration
    -0.57
    into
    -0.51
     into
    -0.50
     BoxDecoration
    -0.49
     autorytatywna
    -0.49
     Invisalign
    -0.46
    idhi
    -0.46
    bibitem
    -0.46
    POSITIVE LOGITS
     from
    1.91
    from
    1.38
     FROM
    1.31
     dari
    1.22
     From
    1.20
    จาก
    1.20
    From
    1.14
     khỏi
    1.13
     från
    1.10
    从
    1.07
    Activations Density 1.544%

    No Known Activations