© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14611
    Prev
    Next
    INDEX
    Explanations

    words related to scientific or technical processes

    oai_token-act-pair · gemini-2.0-flash

    code related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    WebMethod
    -0.53
    ⓘ
    -0.51
    >{@
    -0.51
    รม
    -0.48
     Kowal
    -0.48
    ADELPHIA
    -0.47
     informaron
    -0.46
    ();?>
    -0.46
     soát
    -0.46
     प्रदेश
    -0.45
    POSITIVE LOGITS
    BufferException
    0.66
    ArgsConstructor
    0.60
     diffus
    0.56
    DoubleQuotes
    0.54
     sed
    0.53
     DIFF
    0.53
     diffuse
    0.52
    Datuak
    0.51
    DIFF
    0.50
     Diffusion
    0.50
    Activations Density 3.110%

    No Known Activations