© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11037
    Prev
    Next
    INDEX
    Explanations

    words commonly associated with card making

    oai_token-act-pair · gemini-2.0-flash

    Art, printing, design

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ombie
    -0.72
     vertes
    -0.66
     NgModule
    -0.65
     ſtand
    -0.64
     autorytatywna
    -0.63
    rifuge
    -0.63
     onCancelled
    -0.62
     ſmall
    -0.62
     Chriftian
    -0.61
    KommentareTeilen
    -0.60
    POSITIVE LOGITS
     SAB
    0.42
    Salt
    0.41
     simplex
    0.41
    ัต
    0.40
     '{@
    0.39
    endmodule
    0.38
     trans
    0.37
    Li
    0.37
     IBS
    0.37
     '*':
    0.37
    Activations Density 1.322%

    No Known Activations