© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12018
    Prev
    Next
    INDEX
    Explanations

    equations and related mathematical terms in a formal paper

    oai_token-act-pair · gemini-2.0-flash

    mathematical equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    >{@
    -0.56
     MyBatis
    -0.50
    RuleContext
    -0.48
    GIVEREF
    -0.47
     ModelRenderer
    -0.47
     piggy
    -0.47
    Pener
    -0.47
    ogli
    -0.46
     IDS
    -0.46
     Aids
    -0.46
    POSITIVE LOGITS
    
    0.67
    GEBURTSDATUM
    0.65
    FunctionFlags
    0.63
    RTDA
    0.54
    GraphicsUnit
    0.54
    AndEndTag
    0.54
    aktur
    0.52
    MessageTagHelper
    0.52
    verifyException
    0.52
    __(/*!
    0.51
    Activations Density 9.234%

    No Known Activations