© 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. 14513
    Prev
    Next
    INDEX
    Explanations

    words and numbers related to sports and election results

    oai_token-act-pair · gemini-2.0-flash

    programming or technical terms in software development

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

    teams and competition

    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
    kshake
    -0.43
     Inc
    -0.43
    au
    -0.42
    inc
    -0.40
     klicken
    -0.39
     looked
    -0.38
    A
    -0.37
    şen
    -0.36
     unittest
    -0.36
    Inc
    -0.36
    POSITIVE LOGITS
    MigrationBuilder
    0.81
     snippetHide
    0.77
     CreateTagHelper
    0.75
    
    0.75
     ModelExpression
    0.74
    Hochspringen
    0.72
     мәкал
    0.70
    itudinal
    0.69
     BorderRadius
    0.69
     obtaining
    0.69
    Activations Density 2.155%

    No Known Activations