© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13725
    Prev
    Next
    INDEX
    Explanations

    descriptions of buildings including dimensions and materials

    oai_token-act-pair · gemini-2.0-flash

    building story

    np_max-act-logits · gemini-2.0-flash

    words related to "story" or "stories"

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    AutoScale
    -0.57
    DockStyle
    -0.56
     Normdatei
    -0.56
     AssemblyTitle
    -0.55
     colorWith
    -0.53
    UnusedPrivate
    -0.53
    Веду
    -0.53
    MessageTagHelper
    -0.52
    webElementXpaths
    -0.52
    exitRule
    -0.52
    POSITIVE LOGITS
     story
    1.75
     stories
    1.64
    Story
    1.54
    story
    1.53
     Story
    1.48
     STORY
    1.48
    STORY
    1.44
    stories
    1.42
     Stories
    1.38
    Stories
    1.30
    Activations Density 1.374%

    No Known Activations