© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8970
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or crediting people or funding agencies

    oai_token-act-pair · gemini-2.0-flash

    acknowledgements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     THANK
    -1.19
     thank
    -1.19
     thanking
    -1.09
    thank
    -1.06
     gratitude
    -1.03
     Thank
    -1.02
     THANKS
    -1.00
    Thank
    -1.00
     thanked
    -0.99
     congratulations
    -0.97
    POSITIVE LOGITS
     bulunabilir
    0.47
    holung
    0.45
     StringTokenizer
    0.42
    dziel
    0.41
    liceerd
    0.40
    ustering
    0.40
     strick
    0.40
    arily
    0.40
    طنين
    0.39
    habits
    0.39
    Activations Density 1.022%

    No Known Activations