© 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. 3220
    Prev
    Next
    INDEX
    Explanations

    phrases using "get" that suggest doing or achieving something

    oai_token-act-pair · gemini-2.0-flash

    terms related to initiating or progressing tasks

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

    Something starting

    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
    SourceChecksum
    -0.66
     Remains
    -0.65
     femininos
    -0.65
     femininas
    -0.62
     idleness
    -0.61
    rawDesc
    -0.61
     termica
    -0.59
     houver
    -0.59
     rând
    -0.59
     oreille
    -0.59
    POSITIVE LOGITS
     started
    0.84
     done
    0.60
     STARTED
    0.57
    +#+#
    0.56
    started
    0.56
     Started
    0.56
     changed
    0.56
     figured
    0.54
     moved
    0.54
     prepared
    0.51
    Activations Density 0.658%

    No Known Activations