© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2485
    Prev
    Next
    INDEX
    Explanations

    terms related to software licenses and bug reports

    oai_token-act-pair · gemini-2.0-flash

    say "and"

    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
     et
    -1.63
     та
    -1.04
    et
    -1.02
     ET
    -0.93
     Et
    -0.92
    Et
    -0.92
    yntaxException
    -0.82
     ed
    -0.82
    sizeCache
    -0.81
    RenderAtEndOf
    -0.81
    POSITIVE LOGITS
     as
    0.70
     i
    0.50
     doPost
    0.43
     together
    0.41
     un
    0.39
    createServer
    0.39
    together
    0.39
     plus
    0.36
    Открыть
    0.36
    plus
    0.36
    Activations Density 0.493%

    No Known Activations