© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10010
    Prev
    Next
    INDEX
    Explanations

    the word "poll" or "ballot" possibly associated with voting

    oai_token-act-pair · gemini-2.0-flash

    poll

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.01
     the
    -0.86
     they
    -0.73
     braccia
    -0.69
     there
    -0.69
     Romains
    -0.68
     pronti
    -0.63
     Grecs
    -0.62
     it
    -0.59
     preghiera
    -0.59
    POSITIVE LOGITS
    XmlAccessType
    0.89
    moiselle
    0.85
    sidemargin
    0.82
     inev
    0.80
    autique
    0.79
    istoitu
    0.77
     Gae
    0.75
     migrate
    0.75
    =-=-=-=-
    0.75
     Leningrad
    0.74
    Activations Density 1.831%

    No Known Activations