© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11479
    Prev
    Next
    INDEX
    Explanations

    code and programming jargon

    oai_token-act-pair · gemini-2.0-flash

    itemId

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    extAlignment
    -0.59
    {...
    -0.56
    AxisAlignment
    -0.55
    ịch
    -0.55
     Če
    -0.52
    stel
    -0.52
    ]._
    -0.51
     doInBackground
    -0.49
    RectangleBorder
    -0.49
    שט
    -0.49
    POSITIVE LOGITS
     Chwiliwch
    0.54
     lenker
    0.54
     "..\..\..\
    0.53
    masing
    0.52
    ьаж
    0.51
    PerformLayout
    0.51
    getSupport
    0.50
    ništ
    0.50
    gonic
    0.49
    XtraGrid
    0.47
    Activations Density 6.287%

    No Known Activations