© 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. 9816
    Prev
    Next
    INDEX
    Explanations

    words related to on-line content, but specifically including reviews, commentary, information and technology from on-line sources

    oai_token-act-pair · gemini-2.0-flash

    conditional phrases

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

    if

    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
    __':
    -0.72
     referenties
    -0.68
    __':
    -0.67
     noDo
    -0.60
    __":
    -0.59
    __":
    -0.59
     doInBackground
    -0.56
    OGND
    -0.56
    rrggbb
    -0.55
    atase
    -0.55
    POSITIVE LOGITS
     if
    2.42
    if
    1.91
     If
    1.84
    If
    1.73
     если
    1.62
     jika
    1.61
     dacă
    1.59
     nếu
    1.56
    如果
    1.41
     якщо
    1.40
    Activations Density 2.614%

    No Known Activations