© 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. 10247
    Prev
    Next
    INDEX
    Explanations

    phrases denoting a lack of understanding or a process in progress

    oai_token-act-pair · gemini-2.0-flash

    well

    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
    Negative Logits
     better
    -1.11
    UserScript
    -1.07
     disambiguazione
    -1.04
    better
    -1.00
     mieux
    -0.99
     beſt
    -0.99
    Better
    -0.96
    InitVars
    -0.96
     EconPapers
    -0.93
     best
    -0.92
    POSITIVE LOGITS
    c
    0.38
    rt
    0.37
     hurt
    0.36
    Det
    0.36
    dbus
    0.35
     operacional
    0.35
    x
    0.35
     представля
    0.34
    avanaugh
    0.34
    lesi
    0.34
    Activations Density 3.191%

    No Known Activations