© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16357
    Prev
    Next
    INDEX
    Explanations

    words related to dependability or long-term performance

    oai_token-act-pair · gemini-2.0-flash

    reliability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Âge
    -0.66
    TypedDataSet
    -0.62
     **/
    -0.56
     SSM
    -0.56
    InitVars
    -0.56
     BoxFit
    -0.56
     InputDecoration
    -0.56
     ſeveral
    -0.55
    ielli
    -0.54
     Anſ
    -0.54
    POSITIVE LOGITS
    دانشنامهٔ
    0.64
     Reliability
    0.59
    Reliability
    0.57
    Viitteet
    0.54
    AndEndTag
    0.54
     reliability
    0.52
    Bronnen
    0.51
    vailability
    0.50
     fiabilidad
    0.49
    pushFollow
    0.49
    Activations Density 2.333%

    No Known Activations