© 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. 8667
    Prev
    Next
    INDEX
    Explanations

    proper nouns and common reporting verbs used by news outlets

    oai_token-act-pair · gemini-2.0-flash

    miscellaneous content patterns

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

    News articles

    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
     Monfieur
    -0.85
     MainAxisSize
    -0.85
     Jefus
    -0.82
    sidemargin
    -0.80
    enderror
    -0.77
    PMailer
    -0.75
     snippetHide
    -0.75
    windowFixed
    -0.72
     autorytatywna
    -0.72
    styleType
    -0.72
    POSITIVE LOGITS
     encountered
    0.52
    ais
    0.50
     c
    0.47
    O
    0.46
    бю
    0.46
     identi
    0.46
    Ah
    0.46
     C
    0.45
     Bus
    0.45
     र
    0.45
    Activations Density 2.891%

    No Known Activations