© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12563
    Prev
    Next
    INDEX
    Explanations

    a mixture of named entities, location descriptions, and some seemingly random words

    oai_token-act-pair · gemini-2.0-flash

    multiple languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    NewUrlParser
    -0.42
    PreAuthorize
    -0.39
    |[]
    -0.38
    inc
    -0.35
    ņas
    -0.35
     calldata
    -0.35
    Chief
    -0.35
    je
    -0.35
    men
    -0.35
    Dak
    -0.34
    POSITIVE LOGITS
    EndProject
    0.79
     INTERESAR
    0.73
    ſtanding
    0.69
     вікі
    0.66
    elemField
    0.66
     AssemblyCompany
    0.65
    Демографія
    0.65
     الحره
    0.65
     nahilalakip
    0.65
    ificantly
    0.64
    Activations Density 0.482%

    No Known Activations