© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14107
    Prev
    Next
    INDEX
    Explanations

    lines in java-style documentation that start with "@" and include parameter explanations, return values, and links, along with Tuple structures

    oai_token-act-pair · gemini-2.0-flash

    @

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    polation
    -0.66
    transQ
    -0.63
    tagHelper
    -0.63
    UrlResolution
    -0.63
     sat
    -0.62
    oires
    -0.59
    itecture
    -0.59
     '\\;'
    -0.59
    tagHelperRunner
    -0.58
    éphane
    -0.57
    POSITIVE LOGITS
    global
    0.59
    pa
    0.59
    p
    0.52
     boden
    0.46
    param
    0.45
    params
    0.45
     acoper
    0.45
    do
    0.44
    P
    0.43
     posibil
    0.43
    Activations Density 2.383%

    No Known Activations