© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2631
    Prev
    Next
    INDEX
    Explanations

    instances of illegal or unethical taking or receiving of items

    oai_token-act-pair · gemini-2.0-flash

    Improper activities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     FetchType
    -0.53
    viewDidLoad
    -0.53
    itrile
    -0.52
     estimés
    -0.52
    jsonwebtoken
    -0.52
    MLLoader
    -0.51
    ValueStyle
    -0.49
    merate
    -0.47
    umato
    -0.47
    Gemeinden
    -0.47
    POSITIVE LOGITS
    Hozzáférés
    0.67
    NUMX
    0.63
     Vikipedi
    0.60
    tvguidetime
    0.60
    省市镇
    0.57
     Савезне
    0.56
    RefNanny
    0.56
     Wikimedijinoj
    0.55
    DeleteBehavior
    0.53
     chop
    0.52
    Activations Density 1.191%

    No Known Activations