© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9961
    Prev
    Next
    INDEX
    Explanations

    phrases that express regret about missed opportunities

    oai_token-act-pair · gemini-2.0-flash

    now, nothing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    دانشنامهٔ
    -0.72
    expandindo
    -0.72
    Geplaatst
    -0.69
     ExecuteAsync
    -0.68
    OGND
    -0.68
    تقاوى
    -0.67
    rrggbb
    -0.67
    rovnik
    -0.66
    Tikang
    -0.64
     imageNamed
    -0.63
    POSITIVE LOGITS
     erwar
    0.46
    protected
    0.45
    jadinya
    0.41
    Protected
    0.41
     sahabat
    0.40
    KommentareTeilen
    0.39
     protegido
    0.38
    reet
    0.38
    liegt
    0.38
    databinding
    0.38
    Activations Density 0.105%

    No Known Activations