© 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. 14025
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to obligation and decisions

    oai_token-act-pair · gemini-2.0-flash

    Relating to "hang"

    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
     getField
    -0.54
     Coke
    -0.53
    으면
    -0.52
    영어
    -0.51
     ContentValues
    -0.51
     setCode
    -0.50
     nargin
    -0.48
    τρι
    -0.48
     coke
    -0.47
     verhind
    -0.47
    POSITIVE LOGITS
     hang
    1.72
     hung
    1.68
     hanging
    1.57
     hangs
    1.52
     HANG
    1.48
     Hanging
    1.41
    hanging
    1.34
    Hang
    1.34
    Hanging
    1.34
     Hang
    1.34
    Activations Density 2.938%

    No Known Activations