© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3900
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly related to testing frameworks and syntax

    oai_token-act-pair · gemini-2.0-flash

    programming terminology related to functions and objects

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

    assertions

    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
    lej
    -0.53
    Попис
    -0.52
    Indented
    -0.48
     Twisted
    -0.48
    хал
    -0.48
     calendriers
    -0.47
    hoeddwyd
    -0.47
    ds
    -0.47
    centralwidget
    -0.45
    Билгалдахарш
    -0.45
    POSITIVE LOGITS
     snippetHide
    0.76
     actionMode
    0.73
     whoſe
    0.72
     Theſe
    0.70
     Efq
    0.69
    CompleteListener
    0.66
    ſelf
    0.64
     raiſ
    0.63
     Monfieur
    0.60
     himſelf
    0.60
    Activations Density 4.191%

    No Known Activations