© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3745
    Prev
    Next
    INDEX
    Explanations

    numbers in tables, bullet points, or lists

    oai_token-act-pair · gemini-2.0-flash

    Symbols and varied content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     co
    -0.78
     an
    -0.75
     «
    -0.74
     I
    -0.71
     a
    -0.71
     der
    -0.71
     in
    -0.70
     al
    -0.69
     his
    -0.69
     mit
    -0.69
    POSITIVE LOGITS
     stället
    1.00
     varandra
    0.94
     aikaa
    0.88
     barnen
    0.86
     Anſ
    0.85
     hendes
    0.84
     Diſ
    0.84
     Reſ
    0.81
     Shakspeare
    0.81
     mukana
    0.78
    Activations Density 2.567%

    No Known Activations