© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2027
    Prev
    Next
    INDEX
    Explanations

    instances of people searching, hoping, looking or trying to for things

    oai_token-act-pair · gemini-2.0-flash

    searching and hoping

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    SBATCH
    -1.10
     MonoBehaviour
    -0.83
    Robots
    -0.79
    IndentedString
    -0.76
     Robots
    -0.72
    RectangleBorder
    -0.72
     rospy
    -0.69
     Robot
    -0.68
     robots
    -0.68
     صوتيه
    -0.67
    POSITIVE LOGITS
    legen
    0.47
    anar
    0.45
     layer
    0.44
    olk
    0.43
     department
    0.43
     kir
    0.42
    ikum
    0.42
     natural
    0.41
     counter
    0.41
     Meille
    0.40
    Activations Density 1.539%

    No Known Activations