© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2935
    Prev
    Next
    INDEX
    Explanations

    words related to art, attachments/connections, code, and law/politics

    oai_token-act-pair · gemini-2.0-flash

    join / joining

    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
     beginnetje
    -0.84
    aarrggbb
    -0.74
    AndEndTag
    -0.71
    tvguidetime
    -0.66
     defaultstate
    -0.64
    Билгалдахарш
    -0.64
     kaarangay
    -0.64
     EconPapers
    -0.63
    protoimpl
    -0.60
    الصفحه
    -0.60
    POSITIVE LOGITS
     join
    2.22
     joined
    2.17
     joining
    2.03
     joins
    2.02
     Join
    1.91
    Join
    1.88
     Joining
    1.80
    join
    1.78
     JOIN
    1.74
    Joining
    1.73
    Activations Density 6.481%

    No Known Activations