© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2454
    Prev
    Next
    INDEX
    Explanations

    words related to movies and going to the cinema

    oai_token-act-pair · gemini-2.0-flash

    entertainment and audiences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    rungsseite
    -0.53
    igshid
    -0.52
    EndProject
    -0.51
     насељу
    -0.49
    מבר
    -0.49
     ventre
    -0.48
    ReusableCell
    -0.47
    ValueGeneration
    -0.47
    CloseOperation
    -0.46
    γράφ
    -0.46
    POSITIVE LOGITS
     viewer
    0.57
     viewers
    0.53
     tartalomajánló
    0.51
     purchasers
    0.50
     zostać
    0.50
     منت
    0.49
     Hạ
    0.49
     buyers
    0.49
     Buyers
    0.49
    évaluateur
    0.48
    Activations Density 2.205%

    No Known Activations