© 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. 7379
    Prev
    Next
    INDEX
    Explanations

    the letter 'h' preceded by another letter

    oai_token-act-pair · gemini-2.0-flash

    rare animal names or identifiers

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

    Random/extracted 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
     nakalista
    -0.91
     doInBackground
    -0.66
    endphp
    -0.66
     VIAF
    -0.62
     bezeichneter
    -0.59
     Autorizaciones
    -0.59
     TextInputType
    -0.58
    eabouts
    -0.57
     مرئيه
    -0.56
    alus
    -0.55
    POSITIVE LOGITS
    Geplaatst
    0.63
    b
    0.45
     niega
    0.44
     corriente
    0.43
    weza
    0.43
    はじめに
    0.41
     Formación
    0.40
    oubliez
    0.40
    fitrión
    0.39
     aucune
    0.39
    Activations Density 0.653%

    No Known Activations