© 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. 11216
    Prev
    Next
    INDEX
    Explanations

    words or phrases signifying gratitude

    oai_token-act-pair · gemini-2.0-flash

    programming help

    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
     advance
    -1.86
     Advance
    -1.80
    Advance
    -1.74
    advance
    -1.63
     ADVANCE
    -1.60
     AHEAD
    -1.58
     Ahead
    -1.55
     Forward
    -1.53
     ahead
    -1.52
    Forward
    -1.49
    POSITIVE LOGITS
    enumii
    0.50
     بنا
    0.49
    rne
    0.48
    Ad
    0.46
    toCharArray
    0.46
    헌
    0.44
     Ad
    0.43
    Cryptography
    0.42
    TagMode
    0.42
    جویان
    0.40
    Activations Density 1.958%

    No Known Activations