© 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. 11904
    Prev
    Next
    INDEX
    Explanations

    references to people who used to hold certain positions

    oai_token-act-pair · gemini-2.0-flash

    words related to former roles or positions

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

    former

    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
    بوابة
    -0.60
    BeginContext
    -0.59
    
    
    -0.55
     actualmente
    -0.55
     onPostExecute
    -0.52
     rapides
    -0.52
     iscri
    -0.52
     attuale
    -0.51
     attualmente
    -0.50
     sfera
    -0.50
    POSITIVE LOGITS
    ecutive
    0.63
    IZONT
    0.59
     governor
    0.58
    AddTagHelper
    0.58
    embeds
    0.57
     employee
    0.56
    onnaissance
    0.56
    loyee
    0.56
    itness
    0.55
    polator
    0.55
    Activations Density 1.988%

    No Known Activations