© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10388
    Prev
    Next
    INDEX
    Explanations

    scientific results or conclusions in biology, chemistry, or material science papers.

    oai_token-act-pair · gemini-2.0-flash

    research findings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    LabelTagHelper
    -0.64
    addSubview
    -0.63
    RuleContext
    -0.61
    OrBuilder
    -0.61
    Salta
    -0.59
     invokingState
    -0.59
    ształ
    -0.58
    Ска
    -0.56
    AccessorTable
    -0.56
    PyExc
    -0.55
    POSITIVE LOGITS
     AspNetCore
    0.59
    AnimationsModule
    0.56
     rius
    0.55
    پیوند
    0.49
    টি
    0.47
    origins
    0.46
    IBOutlet
    0.46
    isNameExpr
    0.43
     "..\..\
    0.43
    <?
    0.43
    Activations Density 4.079%

    No Known Activations