© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12422
    Prev
    Next
    INDEX
    Explanations

    various kinds of code or mathematical notation

    oai_token-act-pair · gemini-2.0-flash

    code/math

    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
    ↵↵
    -0.46
    </em>
    -0.42
    Nat
    -0.42
    if
    -0.42
     Nat
    -0.40
     (
    -0.38
     nat
    -0.38
    ,
    -0.37
    .
    -0.37
    <sup>
    -0.35
    POSITIVE LOGITS
     صوتيه
    1.33
    存于互联网档案馆
    1.15
     ModelExpression
    1.10
     незавершена
    1.05
    UnsafeEnabled
    1.01
    AddTagHelper
    0.99
    kháu
    0.99
     myſelf
    0.98
     ſtate
    0.98
     تضيفلها
    0.97
    Activations Density 14.595%

    No Known Activations