© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1843
    Prev
    Next
    INDEX
    Explanations

    conversational text in French and related language codes

    oai_token-act-pair · gemini-2.0-flash

    Multiple languages and code

    np_max-act-logits · gemini-2.0-flash

    French

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109

    nonstandard characters

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     an
    -0.24
     a
    -0.24
     his
    -0.23
     the
    -0.23
     --
    -0.19
    Is
    -0.18
     her
    -0.17
    -0.17
     as
    -0.17
     <
    -0.17
    POSITIVE LOGITS
     Shakspeare
    1.25
     ―――――
    1.16
     Theſe
    1.12
    MLLoader
    1.09
     ་་
    1.08
     Cæsar
    1.07
    RectangleBorder
    1.06
     Мексичка
    1.05
     BoxFit
    1.04
     Anſ
    1.01
    Activations Density 6.048%
    No Known Activations