© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1304
    Prev
    Next
    INDEX
    Explanations

    words and phrases describing car features and models

    oai_token-act-pair · gemini-2.0-flash

    Car/motorcycle features

    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
     دیکھیے
    -0.90
     AssemblyCulture
    -0.87
     dAtA
    -0.84
    Tikang
    -0.81
    EDEFAULT
    -0.81
    KURZBESCHREIBUNG
    -0.81
     rospy
    -0.77
    BeginContext
    -0.76
    ImageContext
    -0.76
    onViewCreated
    -0.75
    POSITIVE LOGITS
    +"'
    0.51
    databinding
    0.46
    getreten
    0.40
     particulier
    0.40
     lived
    0.39
    來的
    0.38
     live
    0.38
     preview
    0.38
     si
    0.37
    arden
    0.37
    Activations Density 3.593%

    No Known Activations