© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7304
    Prev
    Next
    INDEX
    Explanations

    mentions of wanting something for others, or giving direction

    oai_token-act-pair · gemini-2.0-flash

    words related to uncertainty and decision-making

    np_token-act-pair-logits · gpt-4o-mini

    then

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     initComponents
    -0.82
    ]--;
    -0.81
    expandindo
    -0.80
     дописавши
    -0.74
    (!__
    -0.69
    पया
    -0.68
    ähig
    -0.66
     oprot
    -0.65
    Kaieteur
    -0.65
    SequentialGroup
    -0.65
    POSITIVE LOGITS
     then
    4.09
    then
    3.33
    Then
    3.28
     Then
    3.25
     THEN
    3.00
    THEN
    2.64
     entonces
    2.48
     dann
    2.42
     então
    2.36
     سپس
    2.25
    Activations Density 10.887%

    No Known Activations