© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9209
    Prev
    Next
    INDEX
    Explanations

    SFML (Simple and Fast Multimedia Library) code snippets

    oai_token-act-pair · gemini-2.0-flash

    California places

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    tagHelperRunner
    -0.91
     nakalista
    -0.71
    setVerticalGroup
    -0.67
     ddelweddau
    -0.64
    ConstraintMaker
    -0.63
    fjspx
    -0.63
    EDEFAULT
    -0.62
     resourceCulture
    -0.62
    TestingModule
    -0.60
    IntoConstraints
    -0.59
    POSITIVE LOGITS
     SF
    0.88
     Bay
    0.82
    SF
    0.82
     Sacramento
    0.79
    Sacramento
    0.75
     San
    0.74
    Bay
    0.73
     bay
    0.72
     BART
    0.71
     UC
    0.70
    Activations Density 0.671%

    No Known Activations