© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4473
    Prev
    Next
    INDEX
    Explanations

    code snippets where configuration settings are being utilized

    oai_token-act-pair · gemini-2.0-flash

    punctuation/brackets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     оригіналу
    -0.57
    原始内容存档于
    -0.47
     Union
    -0.47
    <bos>
    -0.47
    
    -0.46
    moed
    -0.46
     lean
    -0.45
    cott
    -0.44
     Branch
    -0.44
     Chamber
    -0.44
    POSITIVE LOGITS
    gdx
    0.67
    \{\\
    0.63
     épis
    0.60
     يتيمه
    0.59
     createSlice
    0.57
     frontale
    0.56
     overlying
    0.56
     Colgate
    0.55
     accompagné
    0.55
     fread
    0.54
    Activations Density 1.517%

    No Known Activations