© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7334
    Prev
    Next
    INDEX
    Explanations

    positive sentiment and opinion in writing.

    oai_token-act-pair · gemini-2.0-flash

    s

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     SURE
    -0.54
    /).
    -0.49
    ')).
    -0.48
     sure
    -0.48
    点此举报
    -0.47
    =?";
    -0.46
     ?";
    -0.46
    /',
    -0.45
    ắc
    -0.45
    '],$
    -0.44
    POSITIVE LOGITS
    sizeCache
    0.73
    OGND
    0.68
    featureID
    0.66
    shutil
    0.66
    Datuak
    0.65
    elemField
    0.64
     CreateTagHelper
    0.60
    ValueGeneration
    0.60
    Revenir
    0.60
     féminine
    0.59
    Activations Density 2.631%

    No Known Activations