© 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. 2910
    Prev
    Next
    INDEX
    Explanations

    information about car specifications such as engine type, capacity, or dimensions

    oai_token-act-pair · gemini-2.0-flash

    car engines

    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
    Personendaten
    -0.80
     насеље
    -0.68
     Biôgrafia
    -0.65
     religieuse
    -0.61
     CreateTagHelper
    -0.59
     tongues
    -0.59
     cowardice
    -0.58
    /***/
    -0.57
     Chwiliwch
    -0.57
     kaarangay
    -0.56
    POSITIVE LOGITS
    initializeApp
    0.53
    principalColumn
    0.52
    Datuak
    0.50
    MessageOf
    0.47
     виправивши
    0.45
    Return
    0.42
     inter
    0.41
     فريبيس
    0.40
    $_['
    0.40
     bParam
    0.39
    Activations Density 0.883%

    No Known Activations