© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11525
    Prev
    Next
    INDEX
    Explanations

    words that relate to physical touch, limbs, or body parts, sometimes in the context of force and violence

    oai_token-act-pair · gemini-2.0-flash

    animal body parts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     noDo
    -0.63
    uckoo
    -0.54
     useNavigate
    -0.53
    unción
    -0.52
    URIDAD
    -0.50
    crimination
    -0.49
    Begriffsklä
    -0.48
     utafitiHapana
    -0.47
    NECTION
    -0.47
     reven
    -0.47
    POSITIVE LOGITS
    رشف
    0.64
     CreateTagHelper
    0.60
    ]){
    0.60
    ]:
    0.59
    '):
    0.58
    reactstrap
    0.56
     الاطلاع
    0.56
    migrationBuilder
    0.56
    tableFuture
    0.56
     tangan
    0.55
    Activations Density 1.474%

    No Known Activations