© 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. 8483
    Prev
    Next
    INDEX
    Explanations

    a list of names

    oai_token-act-pair · gemini-2.0-flash

    scientific papers

    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
    AndEndTag
    -0.80
    зулта
    -0.73
    CodedInputStream
    -0.70
    GenerationType
    -0.70
     AssemblyCulture
    -0.69
    ClientSize
    -0.69
     GenerationType
    -0.64
    __(/*!
    -0.64
     provato
    -0.63
     nahilalakip
    -0.63
    POSITIVE LOGITS
     Yin
    0.61
     Y
    0.60
     WU
    0.49
     XY
    0.49
     X
    0.48
     YC
    0.46
    Yin
    0.45
     YP
    0.45
     YI
    0.44
     XF
    0.43
    Activations Density 3.730%

    No Known Activations