© 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. 13684
    Prev
    Next
    INDEX
    Explanations

    mixed Arabic/Persian and other language text, possibly code snippets

    oai_token-act-pair · gemini-2.0-flash

    Arabic words expressing preference or choice

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

    code and non-English text

    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
    UnusedPrivate
    -0.99
    sidemargin
    -0.89
     <>",
    -0.81
    OGND
    -0.79
     Numerade
    -0.76
     lenker
    -0.76
    Parcelize
    -0.74
    uxxxx
    -0.74
    ">—
    -0.73
    Abitanti
    -0.73
    POSITIVE LOGITS
     cremallera
    0.42
    Open
    0.39
     gratuitas
    0.37
    handleDelete
    0.36
    (
    0.36
     mundiales
    0.35
     barnen
    0.35
     cercanos
    0.35
    itní
    0.35
     re
    0.34
    Activations Density 1.160%

    No Known Activations