© 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. 9577
    Prev
    Next
    INDEX
    Explanations

    mentions of "take" as well as the awarding of something

    oai_token-act-pair · gemini-2.0-flash

    words related to leaving or walking

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

    walking/leaving

    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
    TintMode
    -0.49
    onesian
    -0.47
     aveug
    -0.46
    onAttach
    -0.46
    άνει
    -0.44
     Leche
    -0.44
    ípios
    -0.44
    inesh
    -0.43
    Filmografia
    -0.42
    askins
    -0.42
    POSITIVE LOGITS
     leaving
    1.50
     walk
    1.45
     walked
    1.43
     Leaving
    1.42
     leave
    1.41
     Leave
    1.39
     walks
    1.38
    leaving
    1.38
    Leaving
    1.38
    Leave
    1.36
    Activations Density 1.198%

    No Known Activations