© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4500
    Prev
    Next
    INDEX
    Explanations

    code related to UI configuration

    oai_token-act-pair · gemini-2.0-flash

    settings and configurations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     setting
    -2.78
     settings
    -2.77
     Setting
    -2.67
     Settings
    -2.59
    setting
    -2.56
    Setting
    -2.53
    settings
    -2.47
     SETTING
    -2.45
    Settings
    -2.33
    SETTING
    -2.30
    POSITIVE LOGITS
    ViewFeatures
    0.64
    EndGlobalSection
    0.53
    Revenir
    0.52
    IntoConstraints
    0.51
    LoadScene
    0.49
    tokio
    0.49
     informée
    0.49
    antMatchers
    0.49
    tvguidetime
    0.48
     arşivlendi
    0.47
    Activations Density 3.250%

    No Known Activations