© 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. 14103
    Prev
    Next
    INDEX
    Explanations

    lab procedure descriptions

    oai_token-act-pair · gemini-2.0-flash

    water-related terms

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

    say water

    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
    +#+#
    -0.79
     dAtA
    -0.63
     NSCoder
    -0.62
    astify
    -0.60
    BeginContext
    -0.59
    itemBuilder
    -0.57
    OGND
    -0.57
    ArgsConstructor
    -0.57
     архивлан
    -0.55
     yyr
    -0.55
    POSITIVE LOGITS
     water
    1.45
    water
    1.12
     drinking
    1.10
    Water
    1.08
     Water
    1.08
     WATER
    1.03
     running
    1.02
     spring
    1.00
     agua
    0.98
     Drinking
    0.98
    Activations Density 1.468%

    No Known Activations