© 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. 7148
    Prev
    Next
    INDEX
    Explanations

    Dutch funding agencies and grant names

    oai_token-act-pair · gemini-2.0-flash

    tokens related to specific programming or technical terms

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

    multiple languages

    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
     Diſ
    -0.92
     Monfieur
    -0.88
     Eſ
    -0.84
     pleaſure
    -0.82
     purpoſe
    -0.80
     Reſ
    -0.77
     Conſ
    -0.75
     الحره
    -0.74
     Majefty
    -0.73
    NewUrlParser
    -0.73
    POSITIVE LOGITS
    Билгалдахарш
    0.49
     мәкал
    0.45
    yntaxException
    0.39
    dicionado
    0.39
    })*/
    0.37
    RestTemplate
    0.37
     ausge
    0.36
     hecho
    0.36
    WriteTagHelper
    0.35
     HSE
    0.35
    Activations Density 0.934%

    No Known Activations