© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7333
    Prev
    Next
    INDEX
    Explanations

    verbs like "want", "try", and "be" preceded or followed by "to"

    oai_token-act-pair · gemini-2.0-flash

    Politics and controversy

    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
    Negative Logits
    Personensuche
    -0.52
    CompleteListener
    -0.51
    LookAnd
    -0.47
    WebServlet
    -0.47
    principalTable
    -0.46
    aarrggbb
    -0.45
    чению
    -0.44
     religiosa
    -0.44
     Carré
    -0.43
     Morten
    -0.43
    POSITIVE LOGITS
     AttributeSet
    0.75
     challenge
    0.65
     CHALLENGE
    0.64
    challenge
    0.61
    iths
    0.60
    cyj
    0.60
    AddTagHelper
    0.59
     Challenge
    0.59
    Challenge
    0.58
    AndEndTag
    0.58
    Activations Density 1.795%

    No Known Activations