© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11635
    Prev
    Next
    INDEX
    Explanations

    questions of whether or not something is true

    oai_token-act-pair · gemini-2.0-flash

    is

    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
     Is
    -0.79
    Is
    -0.78
     فريبيس
    -0.63
     gainera
    -0.62
    ReferenceEquals
    -0.61
    Was
    -0.59
    astify
    -0.59
     Was
    -0.58
    انجليز
    -0.56
    aarrggbb
    -0.56
    POSITIVE LOGITS
    __;
    0.57
     LayoutInflater
    0.55
     handleMessage
    0.54
    ocry
    0.53
    QUIR
    0.52
    ății
    0.51
    Tilt
    0.51
    مود
    0.50
    RetentionPolicy
    0.50
    rog
    0.50
    Activations Density 4.879%

    No Known Activations