© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12834
    Prev
    Next
    INDEX
    Explanations

    the word "depends" and nearby words "than", "upon", and modifiers.

    oai_token-act-pair · gemini-2.0-flash

    depends

    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
     pleaſure
    -1.07
    #+#
    -1.05
    ContextHolder
    -0.98
    ագրություններ
    -0.97
    GraphicsUnit
    -0.97
     itſelf
    -0.94
     становника
    -0.93
     AttributeSet
    -0.91
     raiſ
    -0.90
    ScopeManager
    -0.89
    POSITIVE LOGITS
    ='';
    0.56
    ↵↵
    0.56
    <eos>
    0.56
    -,
    0.55
     [
    0.53
    ».
    0.53
    ="";
    0.53
    )=>{
    0.52
     Up
    0.51
     C
    0.51
    Activations Density 3.123%

    No Known Activations