© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16232
    Prev
    Next
    INDEX
    Explanations

    the javascript keyword 'let' signifying variable declaration

    oai_token-act-pair · gemini-2.0-flash

    let

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    let
    -1.29
     let
    -0.89
     Let
    -0.74
    Let
    -0.70
    z
    -0.70
    LET
    -0.69
    and
    -0.65
    us
    -0.64
    var
    -0.63
    or
    -0.63
    POSITIVE LOGITS
     Theſe
    1.14
     Majefty
    1.07
     myſelf
    1.02
     itſelf
    1.01
    ſelf
    1.01
     Jefus
    1.00
     Anſ
    0.98
     ―――――
    0.96
     Houſe
    0.95
    ſelves
    0.94
    Activations Density 0.517%

    No Known Activations