© 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. 7398
    Prev
    Next
    INDEX
    Explanations

    sentences where the author describes their game development process and initial intentions

    oai_token-act-pair · gemini-2.0-flash

    originally

    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
    AndEndTag
    -0.52
    ValueStyle
    -0.51
    qtype
    -0.42
    verwijspagina
    -0.40
    helm
    -0.40
     linkovi
    -0.40
    XmlAccessorType
    -0.39
    metter
    -0.39
    HtmlAttribute
    -0.38
    弛
    -0.38
    POSITIVE LOGITS
     planned
    1.95
     intended
    1.70
    planned
    1.64
     originally
    1.62
    Originally
    1.59
    intended
    1.47
     Originally
    1.47
    Planned
    1.45
     Intended
    1.44
    originally
    1.40
    Activations Density 1.038%

    No Known Activations