© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1494
    Prev
    Next
    INDEX
    Explanations

    C code defining constants by bitmasking

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash

    FF

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Waray
    -0.58
    Referanser
    -0.57
    GEBURTSDATUM
    -0.56
    tanleria
    -0.56
    providedIn
    -0.54
    ########.
    -0.53
    protoimpl
    -0.52
    DeleteBehavior
    -0.51
    RegistryLite
    -0.50
     newBuilder
    -0.49
    POSITIVE LOGITS
    Cs
    0.89
    C
    0.84
    R
    0.76
    S
    0.73
    EF
    0.73
    E
    0.71
    O
    0.71
    OOO
    0.70
    OOOOOOOO
    0.70
    D
    0.69
    Activations Density 5.361%

    No Known Activations