© 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. 7251
    Prev
    Next
    INDEX
    Explanations

    uses of the word "and" along with pronouns like "I", "we", "it", typically expressing an opinion.

    oai_token-act-pair · gemini-2.0-flash

    will

    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
    nextLine
    -0.52
     next
    -0.46
    ote
    -0.46
    片
    -0.45
     NEXT
    -0.44
    uman
    -0.44
     مغ
    -0.43
    ]").
    -0.43
    uju
    -0.43
    continued
    -0.42
    POSITIVE LOGITS
     will
    2.00
    will
    1.68
    Will
    1.59
     Will
    1.45
     WILL
    1.34
     akan
    1.30
     sẽ
    1.27
    WILL
    1.26
     zullen
    1.18
     будут
    1.09
    Activations Density 2.514%

    No Known Activations