© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4764
    Prev
    Next
    INDEX
    Explanations

    the word "third" or descriptions of fractions

    oai_token-act-pair · gemini-2.0-flash

    third

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     third
    -2.42
    third
    -2.22
     fourth
    -2.20
    Third
    -2.19
     fifth
    -2.05
     Third
    -2.03
     THIRD
    -1.95
     sixth
    -1.93
    fourth
    -1.88
    Fourth
    -1.88
    POSITIVE LOGITS
    Билгалдахарш
    0.79
    FormTagHelper
    0.78
    ViewFeatures
    0.73
    fjspx
    0.73
    rrggbb
    0.73
     VIDEOTAPE
    0.73
     &___
    0.72
    ########.
    0.72
     nahilalakip
    0.71
    openhague
    0.71
    Activations Density 1.617%

    No Known Activations