© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14306
    Prev
    Next
    INDEX
    Explanations

    punctuation and articles occurring after certain seemingly arbitrarily chosen words

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    enterOuterAlt
    -0.63
    SharedCtor
    -0.59
    DECREF
    -0.58
    ReferenceEquals
    -0.54
    рс
    -0.53
    ThroughAttribute
    -0.53
    Slf
    -0.52
    UIControlState
    -0.47
     NSCoder
    -0.47
    AddField
    -0.46
    POSITIVE LOGITS
    XmlAccessType
    0.65
     Administrativna
    0.59
    demy
    0.59
     Vikipedi
    0.54
    Sucesor
    0.52
     Faso
    0.52
    expandindo
    0.52
    TagHelper
    0.51
    abestanden
    0.51
    wanych
    0.50
    Activations Density 0.191%

    No Known Activations