© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8537
    Prev
    Next
    INDEX
    Explanations

    named places

    oai_token-act-pair · gemini-2.0-flash

    say [place name]

    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
    HtmlAttribute
    -0.69
     houſe
    -0.69
     purpoſe
    -0.69
    WebServlet
    -0.66
    UnusedPrivate
    -0.65
    LabelTagHelper
    -0.64
     Jefus
    -0.60
    posites
    -0.59
     themſelves
    -0.59
    UrlResolution
    -0.59
    POSITIVE LOGITS
     Wallflower
    0.50
     generales
    0.49
     financières
    0.47
     rekke
    0.46
    atini
    0.46
     espin
    0.46
     spelar
    0.44
    herzog
    0.44
     staat
    0.43
     recientes
    0.43
    Activations Density 1.873%

    No Known Activations