© 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. 7549
    Prev
    Next
    INDEX
    Explanations

    angle brackets and indentation found in code

    oai_token-act-pair · gemini-2.0-flash

    XML or HTML-like tag structures

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

    Code/non-English

    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
     purpoſe
    -0.75
    providedIn
    -0.72
     poffe
    -0.71
    PostInfinity
    -0.71
    Portale
    -0.69
    "]);
    -0.69
     Monfieur
    -0.67
     themſelves
    -0.66
     myſelf
    -0.66
    ſelf
    -0.66
    POSITIVE LOGITS
     CreateTagHelper
    0.73
     autorytatywna
    0.57
     Roskov
    0.48
        
    0.47
     <
    0.46
     []
    0.42
    ποίη
    0.40
    RegressionTest
    0.40
    ofar
    0.39
    middel
    0.39
    Activations Density 0.879%

    No Known Activations