© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12167
    Prev
    Next
    INDEX
    Explanations

    a wide variety of terms across different contexts, with some preference for comparing amounts, code, and personal pronouns near greetings.

    oai_token-act-pair · gemini-2.0-flash

    between

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     MainAxisSize
    -0.56
    didSet
    -0.52
    Tikang
    -0.52
    ագրություններ
    -0.49
    aronder
    -0.47
    LookAnd
    -0.45
    MLLoader
    -0.45
    Източници
    -0.44
    Stocks
    -0.43
     solida
    -0.43
    POSITIVE LOGITS
    RegistryLite
    0.65
    kháu
    0.59
    GEBURTSDATUM
    0.56
    Portail
    0.54
    Dichloropropane
    0.53
    expandindo
    0.53
    ایج
    0.52
    AlterField
    0.52
    Portale
    0.51
    RemoveField
    0.51
    Activations Density 4.521%

    No Known Activations