© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4839
    Prev
    Next
    INDEX
    Explanations

    scenes of affection between women in a leadership position.

    oai_token-act-pair · gemini-2.0-flash

    hand/hold

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    lify
    -0.48
     createSlice
    -0.46
    CompilerServices
    -0.46
     Hust
    -0.46
     Franti
    -0.45
    licos
    -0.45
     Kirby
    -0.45
     autorytatywna
    -0.43
    avel
    -0.42
     Uta
    -0.42
    POSITIVE LOGITS
     hand
    1.36
     Hand
    1.17
    hand
    1.09
     HAND
    1.09
    Hand
    1.05
    HAND
    0.95
     hands
    0.94
     Holding
    0.94
    Holding
    0.91
     holding
    0.87
    Activations Density 0.414%

    No Known Activations