© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10526
    Prev
    Next
    INDEX
    Explanations

    verbs related to obtaining or acquiring as well as those ending in "ing"

    oai_token-act-pair · gemini-2.0-flash

    getting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     getting
    -1.45
    Getting
    -1.35
    getting
    -1.31
     Getting
    -1.31
     GETTING
    -1.20
     becoming
    -1.13
    becoming
    -0.96
     Becoming
    -0.92
    GETTING
    -0.90
     obtaining
    -0.83
    POSITIVE LOGITS
    ⓧ
    0.81
    aarrggbb
    0.73
    harusnya
    0.62
    ymce
    0.56
     sprechen
    0.56
    ENTINA
    0.54
    VideoCapture
    0.54
    lış
    0.53
    wigs
    0.53
    nsyn
    0.52
    Activations Density 1.446%

    No Known Activations