© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15195
    Prev
    Next
    INDEX
    Explanations

    instances of low-cost or negligible expenses

    oai_token-act-pair · gemini-2.0-flash

    costs and errors

    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
     Risks
    -1.03
    Costs
    -1.02
     Costs
    -1.02
    Risks
    -0.98
    costs
    -0.96
     costs
    -0.95
     COSTS
    -0.95
    risks
    -0.94
     risks
    -0.94
     powers
    -0.91
    POSITIVE LOGITS
    ########.
    0.99
     automatiques
    0.77
    TagMode
    0.75
    +#+#
    0.74
     виправивши
    0.73
     acrylique
    0.71
    Advertisements
    0.68
    #+#
    0.66
    fjspx
    0.66
    AddHtmlAttribute
    0.65
    Activations Density 7.019%

    No Known Activations