© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14669
    Prev
    Next
    INDEX
    Explanations

    references to Honda or Pontiac vehicles

    oai_token-act-pair · gemini-2.0-flash

    non-standard text patterns or identifiers

    np_token-act-pair-logits · gpt-4o-mini

    car models

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    }=\{
    -0.47
    риф
    -0.44
     오
    -0.42
    ="//
    -0.42
    撮り
    -0.41
    ότε
    -0.41
     alté
    -0.41
    olí
    -0.41
    tron
    -0.41
    vartis
    -0.41
    POSITIVE LOGITS
     resourceCulture
    0.96
     AssemblyCulture
    0.86
    rungsseite
    0.81
     يتيمه
    0.79
    +#+#
    0.75
    Билгалдахарш
    0.74
    findpost
    0.73
    AddTagHelper
    0.73
    SBATCH
    0.70
     فريبيس
    0.70
    Activations Density 0.483%

    No Known Activations