© 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. 12542
    Prev
    Next
    INDEX
    Explanations

    C++ code

    oai_token-act-pair · gemini-2.0-flash

    boolean variables and flags in code

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

    Code related

    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
     false
    -1.41
     true
    -1.39
    false
    -1.38
    true
    -1.37
    False
    -1.20
    True
    -1.18
     True
    -1.15
     False
    -1.12
    FALSE
    -0.98
     FALSE
    -0.96
    POSITIVE LOGITS
    onActivityResult
    0.69
     b
    0.63
     bol
    0.59
    Geografía
    0.55
     BOL
    0.53
     Lein
    0.52
    bol
    0.52
    BOL
    0.49
     [*]
    0.49
     &[
    0.48
    Activations Density 1.863%

    No Known Activations