© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2582
    Prev
    Next
    INDEX
    Explanations

    the words "what", "do", "we", "you", "I", and "they".

    oai_token-act-pair · gemini-2.0-flash

    Action/doing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     operations
    -0.64
     performed
    -0.63
     actions
    -0.63
     acted
    -0.62
    actions
    -0.60
    <bos>
    -0.58
     الاطلاع
    -0.56
     perform
    -0.54
     action
    -0.54
     thing
    -0.54
    POSITIVE LOGITS
    ształ
    0.71
     المعيارى
    0.68
    醐
    0.68
    الحياه
    0.67
     فريبيس
    0.66
    первых
    0.66
     définiti
    0.64
     تانيه
    0.63
     виправивши
    0.63
     podjela
    0.63
    Activations Density 0.570%

    No Known Activations