© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6204
    Prev
    Next
    INDEX
    Explanations

    mathematical LaTex formulas and code

    oai_token-act-pair · gemini-2.0-flash

    technical terms or programming language elements

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

    code

    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
    im
    -0.45
    様子
    -0.45
     Ejecutivo
    -0.44
     banho
    -0.42
    iman
    -0.41
     Vedi
    -0.41
     Económica
    -0.40
     stages
    -0.40
    ապ
    -0.40
     علشان
    -0.39
    POSITIVE LOGITS
    jooq
    0.80
    IUrlHelper
    0.72
     Italijanski
    0.72
    tvguidetime
    0.71
     disambiguazione
    0.71
    contentLoaded
    0.71
    ########.
    0.70
    TagMode
    0.70
    ⓧ
    0.69
    processable
    0.68
    Activations Density 5.187%

    No Known Activations