© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12410
    Prev
    Next
    INDEX
    Explanations

    a mix of legal citations, code snippets, and possibly some numerical or technical content

    oai_token-act-pair · gemini-2.0-flash

    foreign language

    np_max-act-logits · gemini-2.0-flash
    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
    SourceChecksum
    -1.08
    enumi
    -1.06
     betweenstory
    -1.03
    setVerticalGroup
    -1.01
     مشين
    -0.99
    Tikang
    -0.98
     nahilalakip
    -0.98
    المكان
    -0.97
    LineVCR
    -0.96
     Roskov
    -0.95
    POSITIVE LOGITS
     stället
    0.16
     avoient
    0.09
     vectorielles
    0.09
     étoient
    0.07
     termica
    0.06
     enfans
    0.06
     démocr
    0.05
     varandra
    0.04
     automatiques
    0.02
     vérit
    0.01
    Activations Density 1.761%

    No Known Activations