© 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. 14764
    Prev
    Next
    INDEX
    Explanations

    HTML markup and special characters

    oai_token-act-pair · gemini-2.0-flash

    formatting elements and special characters

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

    code snippets

    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
    findpost
    -0.59
    ⓧ
    -0.59
    hnung
    -0.59
    hamel
    -0.57
     муніципалі
    -0.54
    lyl
    -0.53
    󠁴
    -0.51
    AddTagHelper
    -0.50
    distinct
    -0.49
     disambiguazione
    -0.48
    POSITIVE LOGITS
     الحره
    0.52
     IBRARY
    0.52
    utilisons
    0.51
    Hochspringen
    0.48
    .[/
    0.48
     handleMessage
    0.48
    --)
    0.47
     :.
    0.47
     torchvision
    0.46
     MessageBoxIcon
    0.46
    Activations Density 4.931%

    No Known Activations