© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12513
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude in conversational text

    oai_token-act-pair · gemini-2.0-flash

    Thank you/I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     podjet
    -0.48
     suivantes
    -0.47
     Bär
    -0.45
     Kaye
    -0.44
    。
    -0.44
     Tango
    -0.43
    blage
    -0.43
     Compet
    -0.43
     ffilmiau
    -0.43
    ##
    -0.42
    POSITIVE LOGITS
    +#+#
    0.81
    httphttps
    0.78
    Portale
    0.75
    MigrationBuilder
    0.70
    CodeAttribute
    0.70
    Спољашње
    0.66
     CURIAM
    0.66
    IntoConstraints
    0.66
    styleUrls
    0.65
    SequentialGroup
    0.65
    Activations Density 0.760%

    No Known Activations