© 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. 7246
    Prev
    Next
    INDEX
    Explanations

    descriptions of people moving or showing emotions, especially actions involving hands or arms.

    oai_token-act-pair · gemini-2.0-flash

    Limbs and movement

    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
    MessageOf
    -0.73
    DropTable
    -0.55
     ddelweddau
    -0.53
    dro
    -0.51
    contentLoaded
    -0.51
    reverse
    -0.50
     drop
    -0.49
    Filmographie
    -0.49
    execSQL
    -0.48
     dri
    -0.48
    POSITIVE LOGITS
    InjectAttribute
    0.70
     termica
    0.57
     Mase
    0.56
    égard
    0.56
     pageIndex
    0.54
    󠁢
    0.54
    ěji
    0.53
    läufig
    0.52
     limbs
    0.52
     sztu
    0.51
    Activations Density 1.058%

    No Known Activations