© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4210
    Prev
    Next
    INDEX
    Explanations

    instances of people ensuring things are present for others

    oai_token-act-pair · gemini-2.0-flash

    ensuring needs are met

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     AssemblyCompany
    -0.50
    ędz
    -0.50
    mybatisplus
    -0.48
    VARS
    -0.48
     proposons
    -0.47
    SBATCH
    -0.46
    batore
    -0.45
     ness
    -0.45
    unre
    -0.45
    lagio
    -0.45
    POSITIVE LOGITS
     виправивши
    0.62
    Parcelize
    0.59
    ած
    0.56
    endaftaran
    0.56
    becker
    0.50
    TProtocol
    0.50
     oprot
    0.49
    <?
    0.49
    __*/
    0.47
     cavo
    0.47
    Activations Density 11.249%

    No Known Activations