© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11210
    Prev
    Next
    INDEX
    Explanations

    words and phrases that describe positivity and success

    oai_token-act-pair · gemini-2.0-flash

    Describes contextual transitions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     traités
    -0.58
     bakgrund
    -0.50
     culturali
    -0.50
    CloseOperation
    -0.50
     devrez
    -0.49
     linee
    -0.49
     trasparente
    -0.49
    “
    -0.48
     préf
    -0.48
     commerciali
    -0.48
    POSITIVE LOGITS
    PyExc
    0.63
    fastjson
    0.62
     ddelweddau
    0.62
    TagHelper
    0.56
    ussis
    0.55
    InjectAttribute
    0.54
    MessageOf
    0.54
    HasIndex
    0.54
    发表于
    0.53
    fras
    0.53
    Activations Density 2.894%

    No Known Activations