© 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. 7796
    Prev
    Next
    INDEX
    Explanations

    sentences about a journey, either physical or metaphorical

    oai_token-act-pair · gemini-2.0-flash

    words related to bringing or leading

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

    bring

    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
    Clik
    -0.62
     Subtract
    -0.60
     correctes
    -0.60
     naw
    -0.59
     Refin
    -0.57
     CreateTagHelper
    -0.57
    Anhalt
    -0.56
    phazard
    -0.55
     Queries
    -0.54
     wünsche
    -0.54
    POSITIVE LOGITS
     bringing
    0.90
     brought
    0.89
     brings
    0.88
     bring
    0.87
    bringing
    0.82
     Bringing
    0.79
     lead
    0.77
    Bringing
    0.77
    brought
    0.76
    Brought
    0.74
    Activations Density 1.403%

    No Known Activations