© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3685
    Prev
    Next
    INDEX
    Explanations

    strings of words and separators that appear repeatedly.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    AndEndTag
    -0.45
     nonUne
    -0.44
    __;
    -0.41
    ix
    -0.40
    ViewInit
    -0.40
    isdigit
    -0.40
    setImageBitmap
    -0.40
    indd
    -0.39
    hes
    -0.39
     ويكيميديا
    -0.39
    POSITIVE LOGITS
    tonsoft
    0.72
     كومونز
    0.65
     Encounter
    0.62
     só
    0.60
    deals
    0.60
    حياته
    0.59
    etera
    0.59
     hrs
    0.59
     RSSSF
    0.59
     PopupWindow
    0.59
    Activations Density 0.325%

    No Known Activations