© 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. 5806
    Prev
    Next
    INDEX
    Explanations

    code, particularly associated with variable or object identification

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
     Big
    -0.49
    idazole
    -0.48
    sad
    -0.46
    hasMany
    -0.43
    idah
    -0.42
    /',
    -0.41
    tende
    -0.41
    riding
    -0.41
     bağ
    -0.41
    Big
    -0.41
    POSITIVE LOGITS
     nakalista
    0.90
     AssemblyCompany
    0.87
     الحره
    0.76
     Vedi
    0.73
    matchCondition
    0.71
     chré
    0.69
     Roskov
    0.68
    writeFieldEnd
    0.67
    TestBed
    0.66
     InputDecoration
    0.66
    Activations Density 0.989%

    No Known Activations