© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9543
    Prev
    Next
    INDEX
    Explanations

    subjective active verbs and adjectives in the past tense

    oai_token-act-pair · gemini-2.0-flash

    Past tense verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    bie
    -0.48
    awaiter
    -0.44
    ERT
    -0.43
    vertx
    -0.43
    endforeach
    -0.42
    : 
    -0.42
    SEB
    -0.40
    خواندن
    -0.40
     africaine
    -0.40
     chaîne
    -0.40
    POSITIVE LOGITS
    RegressionTest
    0.84
    contentLoaded
    0.72
    Попис
    0.66
    DJANGO
    0.64
    DockStyle
    0.62
    handleRequest
    0.59
    oulders
    0.59
    ˏ
    0.59
    MessageTagHelper
    0.58
    IDAE
    0.58
    Activations Density 2.224%

    No Known Activations