© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7723
    Prev
    Next
    INDEX
    Explanations

    text discussing natural resource exploitation and probability

    oai_token-act-pair · gemini-2.0-flash

    oil and gas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     CreateTagHelper
    -0.91
     nahilalakip
    -0.90
    migrationBuilder
    -0.85
     désolés
    -0.82
    webElementXpaths
    -0.81
     beginnetje
    -0.81
    ThroughAttribute
    -0.80
    دانشنامهٔ
    -0.78
    UnusedPrivate
    -0.77
     ProtoMessage
    -0.77
    POSITIVE LOGITS
    ondo
    0.37
     und
    0.36
    Nu
    0.34
     SCN
    0.33
     cens
    0.32
     undoing
    0.32
    gak
    0.32
    RTLI
    0.32
     фар
    0.31
    adás
    0.31
    Activations Density 2.287%

    No Known Activations