© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1954
    Prev
    Next
    INDEX
    Explanations

    general, non-specific connecting words and phrases.

    oai_token-act-pair · gemini-2.0-flash

    technical writing

    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
    RegistryLite
    -0.63
     fieldNum
    -0.63
     saites
    -0.56
    AsUp
    -0.54
     ویکی‌پدیا
    -0.51
     daqui
    -0.51
    featureID
    -0.50
     Ause
    -0.50
     proper
    -0.50
    aarrggbb
    -0.49
    POSITIVE LOGITS
    actual
    0.64
    multirow
    0.63
    andExpect
    0.62
    Mui
    0.60
    Personensuche
    0.60
    Actual
    0.57
    ACTUAL
    0.57
    اریخ
    0.55
     onAnimation
    0.53
    änder
    0.53
    Activations Density 1.360%

    No Known Activations