© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3303
    Prev
    Next
    INDEX
    Explanations

    names of people

    oai_token-act-pair · gemini-2.0-flash

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    Parcelize
    -0.60
    MeasureSpec
    -0.60
    WriteTagHelper
    -0.56
     FetchType
    -0.56
    UserScript
    -0.54
     TableColumn
    -0.54
    ThroughAttribute
    -0.54
    ativement
    -0.54
    ArgsConstructor
    -0.53
     BorderSide
    -0.53
    POSITIVE LOGITS
    <bos>
    1.19
     تانيه
    0.56
    }],
    0.48
    ább
    0.46
    ということを
    0.45
    hood
    0.44
    AndEndTag
    0.44
     had
    0.44
    ção
    0.44
    OCH
    0.43
    Activations Density 2.355%

    No Known Activations