© 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. 10371
    Prev
    Next
    INDEX
    Explanations

    sentences containing a conjunction or interjection related to sadness

    oai_token-act-pair · gemini-2.0-flash

    sad/difficult events

    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
    IntoConstraints
    -1.38
     disambiguazione
    -1.34
     lenker
    -1.16
    OGND
    -1.09
    MigrationBuilder
    -1.02
     saites
    -1.01
    ArgsConstructor
    -1.00
    verwijspagina
    -0.97
    TagMode
    -0.96
    findpost
    -0.95
    POSITIVE LOGITS
     c
    0.50
     with
    0.44
     back
    0.43
     a
    0.42
     for
    0.39
    back
    0.39
     touch
    0.38
     an
    0.38
     completely
    0.37
    <eos>
    0.37
    Activations Density 0.928%

    No Known Activations