© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9070
    Prev
    Next
    INDEX
    Explanations

    personal anecdotes

    oai_token-act-pair · gemini-2.0-flash

    future tense verbs 'will'

    np_token-act-pair-logits · gpt-4o-mini

    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_21/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.21.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
    BufferException
    -0.72
    InputTagHelper
    -0.59
    HandlerContext
    -0.57
    ']").
    -0.53
     galt
    -0.52
    }`}>
    -0.51
    nyata
    -0.50
    "=>"
    -0.49
    以上です
    -0.49
    EndContext
    -0.48
    POSITIVE LOGITS
     will
    2.48
    will
    2.02
    Will
    1.88
     Will
    1.80
     akan
    1.63
     WILL
    1.54
     sẽ
    1.53
    WILL
    1.38
     zullen
    1.24
     wil
    1.11
    Activations Density 2.800%

    No Known Activations