© 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. 3596
    Prev
    Next
    INDEX
    Explanations

    words combined with "hand" or words implying order or importance

    oai_token-act-pair · gemini-2.0-flash

    "on the hand"

    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
     Hand
    -2.52
     Hands
    -2.48
    Hand
    -2.45
    HAND
    -2.41
     hands
    -2.39
     hand
    -2.39
     HAND
    -2.36
    Hands
    -2.34
    hands
    -2.34
    hand
    -2.30
    POSITIVE LOGITS
     had
    0.47
    -
    0.35
    らを
    0.31
     disparu
    0.31
     havia
    0.31
     había
    0.30
     entrado
    0.30
     h
    0.30
    ‌
    0.29
     fuga
    0.29
    Activations Density 1.258%

    No Known Activations