© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3006
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and variables

    oai_token-act-pair · gemini-2.0-flash

    formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Wikimedijinoj
    -0.68
    pement
    -0.65
    principalTable
    -0.59
     poveznice
    -0.56
    rungsseite
    -0.55
     виправивши
    -0.54
    AutoScale
    -0.52
    ślę
    -0.51
     BorderSide
    -0.51
    AxisAlignment
    -0.51
    POSITIVE LOGITS
    adaptiveStyles
    0.63
    راط
    0.55
     Samaria
    0.54
    VIAF
    0.54
     propOrder
    0.53
    Tumor
    0.49
     ""));
    0.48
     tumor
    0.47
    Бахар
    0.47
     الحره
    0.46
    Activations Density 3.053%

    No Known Activations