© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11635
    Prev
    Next
    INDEX
    Explanations

    contexts where someone is giving someone else help or instructions

    oai_token-act-pair · gemini-2.0-flash

    words related to selection and choice

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

    choice, selection

    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
    BeginContext
    -0.57
    FontOfSize
    -0.55
    ensores
    -0.47
    իր
    -0.45
    thenReturn
    -0.43
    vänd
    -0.42
     "?"
    -0.42
    IMDG
    -0.41
     TextAppearance
    -0.40
    TagMode
    -0.39
    POSITIVE LOGITS
     choose
    1.99
     choosing
    1.98
     select
    1.93
     chooses
    1.91
     selecting
    1.88
     chose
    1.87
    choose
    1.79
    choosing
    1.77
     Choosing
    1.76
     chosen
    1.74
    Activations Density 3.114%

    No Known Activations