© 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. 13772
    Prev
    Next
    INDEX
    Explanations

    text referencing the mechanics of a tank, especially its treads

    oai_token-act-pair · gemini-2.0-flash

    Programming/Physics

    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
     CreateTagHelper
    -0.59
    évaluateur
    -0.57
    StackNavigator
    -0.55
     оригіналу
    -0.54
    __(/*!
    -0.53
    новништво
    -0.52
    multirow
    -0.52
    +:+
    -0.52
    WebVitals
    -0.51
    dération
    -0.51
    POSITIVE LOGITS
    GEBURTSDATUM
    0.56
    onViewCreated
    0.52
    laught
    0.51
     AppCompatTheme
    0.50
    Activités
    0.49
    Condol
    0.48
     Lander
    0.47
    ランド
    0.47
    DeleteBehavior
    0.47
     lau
    0.46
    Activations Density 3.247%

    No Known Activations