© 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. 5214
    Prev
    Next
    INDEX
    Explanations

    references to the first or third person, and to ideas presented as controversial or aggressive

    oai_token-act-pair · gemini-2.0-flash

    verbs

    np_max-act-logits · gemini-2.0-flash
    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
    EDEFAULT
    -0.66
    MessageState
    -0.62
     picioare
    -0.62
    RegistryLite
    -0.54
     Lightboxes
    -0.54
     définiti
    -0.53
    verwijspagina
    -0.53
     typelib
    -0.52
     fumée
    -0.51
     jspb
    -0.51
    POSITIVE LOGITS
     confirm
    0.82
     accuse
    0.80
     confuse
    0.79
     decompose
    0.79
     write
    0.77
     relocate
    0.77
     verify
    0.74
     promote
    0.74
     create
    0.73
     identify
    0.72
    Activations Density 4.085%

    No Known Activations