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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 61
    Prev
    Next
    INDEX
    Explanations

    various symbols, possibly related to formatting or code

    oai_token-act-pair · gemini-2.0-flash

    code/technical documentation

    np_max-act-logits · gemini-2.0-flash

    space

    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
    ientôt
    -0.42
    GenerationType
    -0.34
    Reuters
    -0.31
    WB
    -0.30
    CoV
    -0.30
    Exc
    -0.30
     aikaa
    -0.29
    Abp
    -0.29
     tulee
    -0.29
    E
    -0.29
    POSITIVE LOGITS
    AndEndTag
    0.57
    contentLoaded
    0.48
    rungsseite
    0.47
     CreateTagHelper
    0.47
    ագրություններ
    0.43
    :✨
    0.42
     Anſ
    0.41
     Table
    0.40
    StoryboardSegue
    0.40
     Theſe
    0.40
    Activations Density 2.706%

    No Known Activations