© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16281
    Prev
    Next
    INDEX
    Explanations

    mentions of organized events or competitions

    oai_token-act-pair · gemini-2.0-flash

    Events and festivals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    AxisAlignment
    -0.66
    AndEndTag
    -0.63
    AddTagHelper
    -0.55
    //
    -0.55
    principalColumn
    -0.52
    shadowOpacity
    -0.52
     HasFactory
    -0.50
     विश्वसनीयता
    -0.50
     oprot
    -0.50
     RouterModule
    -0.49
    POSITIVE LOGITS
     Wayback
    0.62
    giving
    0.52
    Vanjske
    0.51
     lyd
    0.50
     Give
    0.50
     Gives
    0.49
     uLocal
    0.49
    give
    0.48
    Giving
    0.48
     Giving
    0.48
    Activations Density 5.398%

    No Known Activations