© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7904
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to purchasing things online, especially Nuroflex and locations

    oai_token-act-pair · gemini-2.0-flash

    australia, online, uk

    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
    <bos>
    -1.66
     betweenstory
    -0.78
     autorytatywna
    -0.70
     getItemId
    -0.69
    PreInfinity
    -0.65
     */;
    -0.60
    fjspx
    -0.59
     '\\;'
    -0.59
     архивлан
    -0.58
     kaarangay
    -0.56
    POSITIVE LOGITS
    WEBPACK
    0.71
    [toxicity=0]
    0.63
    ProcessEvent
    0.58
     отношению
    0.57
    ;&
    0.57
     []:
    0.57
     protoimpl
    0.55
    mella
    0.54
    displaystyle
    0.53
    __;
    0.53
    Activations Density 0.467%

    No Known Activations