© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8417
    Prev
    Next
    INDEX
    Explanations

    words in academic research contexts associated with studies or discoveries.

    oai_token-act-pair · gemini-2.0-flash

    testing a hypothesis

    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
    Negative Logits
    evidence
    -1.08
    Theory
    -1.02
     Evidence
    -1.02
    Evidence
    -1.02
     Theory
    -1.00
     theory
    -0.99
     evidence
    -0.97
    theory
    -0.94
     EVIDENCE
    -0.89
     theories
    -0.86
    POSITIVE LOGITS
     considérons
    0.46
    InitVars
    0.46
    nonzero
    0.46
    yyy
    0.45
    hnia
    0.45
    InputTagHelper
    0.45
    曖昧さ回避
    0.44
    lha
    0.44
    허
    0.44
    ########.
    0.40
    Activations Density 7.062%

    No Known Activations