© 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. 14294
    Prev
    Next
    INDEX
    Explanations

    words related to body parts, their movement, and discomfort

    oai_token-act-pair · gemini-2.0-flash

    my

    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
    findpost
    -0.61
    Aholisi
    -0.60
    EndContext
    -0.58
    rafa
    -0.55
     shoulder
    -0.55
    []>(
    -0.54
     Jock
    -0.54
     Signalez
    -0.54
     thigh
    -0.54
     postIndex
    -0.54
    POSITIVE LOGITS
     AssemblyTitle
    0.64
     gl
    0.56
    WSGI
    0.55
    ControllerAdvice
    0.49
     abs
    0.49
    ArrowToggle
    0.49
    IntoConstraints
    0.48
    rungsseite
    0.48
    __':
    0.47
     ujednoznacz
    0.47
    Activations Density 0.884%

    No Known Activations