© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3846
    Prev
    Next
    INDEX
    Explanations

    content from blog posts, identifying the structural elements of the posts

    oai_token-act-pair · gemini-2.0-flash

    commission

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     MainAxisSize
    -1.00
    TestingModule
    -0.93
    IntoConstraints
    -0.85
     bezeichneter
    -0.84
     CreateTagHelper
    -0.83
    !*\
    -0.83
    posedge
    -0.81
    InstrumentedTest
    -0.81
     AttributeSet
    -0.81
    MigrationBuilder
    -0.80
    POSITIVE LOGITS
    +
    0.43
     +
    0.41
    hets
    0.41
     ""],
    0.40
    ITCH
    0.39
     generic
    0.38
    </blockquote>
    0.36
     semi
    0.36
    ↵
    0.36
     c
    0.36
    Activations Density 0.787%

    No Known Activations