© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9677
    Prev
    Next
    INDEX
    Explanations

    instances where the author is offering an opinion or interpretation based on observations

    oai_token-act-pair · gemini-2.0-flash

    opinions and viewpoints

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    UserScript
    -0.57
    preloader
    -0.50
    gesehen
    -0.47
    polation
    -0.46
     }}$
    -0.46
    nesota
    -0.46
     rid
    -0.44
    odotus
    -0.44
     pré
    -0.44
     fac
    -0.44
    POSITIVE LOGITS
    <bos>
    0.79
     AssemblyCulture
    0.77
    ItemBackground
    0.70
    DockStyle
    0.64
    Geplaatst
    0.60
     beginnetje
    0.59
    break
    0.56
     الرياضيه
    0.56
    Diwedd
    0.56
    jeuner
    0.53
    Activations Density 1.277%

    No Known Activations