© 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. 8248
    Prev
    Next
    INDEX
    Explanations

    bracketed citations and mathematical equations

    oai_token-act-pair · gemini-2.0-flash

    symbols and special characters in mathematical or technical contexts

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

    mathematical equations

    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
    azin
    -0.57
     duties
    -0.53
     !
    -0.52
    طقة
    -0.51
     dioses
    -0.50
     tyranny
    -0.49
     contexts
    -0.49
     придется
    -0.49
     themselves
    -0.49
     myself
    -0.49
    POSITIVE LOGITS
     виправивши
    1.03
    contentLoaded
    0.91
     سكانية
    0.70
     مرئيه
    0.64
    ayaquil
    0.63
    afficheront
    0.59
    StructEnd
    0.59
     Biôgrafia
    0.59
    AxisAlignment
    0.58
    jsonwebtoken
    0.58
    Activations Density 1.530%

    No Known Activations