© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12643
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to fantasy and comics

    oai_token-act-pair · gemini-2.0-flash

    reincarnation/rebirth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    InputBorder
    -0.76
    tableFuture
    -0.72
    脚注の使い方
    -0.69
     >=",
    -0.68
    ulink
    -0.64
     ExecuteAsync
    -0.64
     BorderRadius
    -0.63
    esgue
    -0.61
    évaluateur
    -0.59
    AccessorTable
    -0.57
    POSITIVE LOGITS
    WithIOException
    0.51
     pé
    0.50
    तान
    0.47
     Trasp
    0.46
    iastes
    0.46
     whiteColor
    0.45
     adhesion
    0.44
    esterno
    0.44
    fahrzeug
    0.44
    unggu
    0.44
    Activations Density 0.267%

    No Known Activations