© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12455
    Prev
    Next
    INDEX
    Explanations

    mentions of family relationships and descriptions of childhood

    oai_token-act-pair · gemini-2.0-flash

    child

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    <bos>
    -0.71
    />";
    -0.65
    eseorang
    -0.63
     Theſe
    -0.58
     />";
    -0.57
    Ђ
    -0.55
     allAfrica
    -0.54
    OGND
    -0.53
    ="@+
    -0.53
    wahati
    -0.53
    POSITIVE LOGITS
    ped
    0.46
    protoimpl
    0.45
    indd
    0.43
    ThroughAttribute
    0.43
     genitori
    0.43
     childhood
    0.42
    ScopeManager
    0.42
    ╔
    0.42
     childs
    0.41
    /*++
    0.41
    Activations Density 0.654%

    No Known Activations