© 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. 2423
    Prev
    Next
    INDEX
    Explanations

    words related to martial arts or Eastern fantasy combat

    oai_token-act-pair · gemini-2.0-flash

    technical terms or elements in scientific contexts

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

    Technical/scientific descriptions

    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
    Personensuche
    -0.82
    AddTagHelper
    -0.74
     betweenstory
    -0.73
    InSection
    -0.70
    BrowserModule
    -0.66
     onCancelled
    -0.66
     combineReducers
    -0.65
    Vtbl
    -0.63
    webElementXpaths
    -0.63
    batis
    -0.62
    POSITIVE LOGITS
    AndEndTag
    0.47
    lovak
    0.44
    }:${
    0.44
     huk
    0.43
     initComponents
    0.42
     cường
    0.41
    ALUM
    0.40
    unsaturated
    0.40
     vacía
    0.39
    音を
    0.39
    Activations Density 0.878%

    No Known Activations