© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6609
    Prev
    Next
    INDEX
    Explanations

    words related to press releases from organizations

    oai_token-act-pair · gemini-2.0-flash

    Online information and news

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     nakalista
    -0.68
     bezeichneter
    -0.59
    AndEndTag
    -0.58
    okości
    -0.56
     becauſe
    -0.55
     насељу
    -0.55
    +#+#
    -0.55
     initComponents
    -0.54
     ADT
    -0.54
    ContentAsync
    -0.54
    POSITIVE LOGITS
    worths
    0.50
    waz
    0.46
     official
    0.46
    满
    0.46
     wes
    0.46
     oficial
    0.45
    worth
    0.45
     inroads
    0.44
    Cleared
    0.44
    fed
    0.44
    Activations Density 0.997%

    No Known Activations