© 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. 7314
    Prev
    Next
    INDEX
    Explanations

    linguistic expressions of potential or requirement, often using modal verbs and the word "to"

    oai_token-act-pair · gemini-2.0-flash

    to

    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
    +:+
    -0.58
     trụ
    -0.52
    PerformLayout
    -0.52
    ütz
    -0.52
     drifting
    -0.51
    GeneratedMessage
    -0.50
    ppled
    -0.50
    urgia
    -0.50
    AddField
    -0.49
     trick
    -0.48
    POSITIVE LOGITS
    sizeCache
    0.54
    ureusement
    0.54
    Bronnen
    0.53
     inflater
    0.53
     ioutil
    0.50
    apimachinery
    0.49
    TestTools
    0.49
     Мексичка
    0.48
    بوابة
    0.48
    TagHelper
    0.47
    Activations Density 13.707%

    No Known Activations