© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5569
    Prev
    Next
    INDEX
    Explanations

    phrases about owning errors or being responsible, as well as contrasting personal versus impersonal finances or experiences.

    oai_token-act-pair · gemini-2.0-flash

    ownership, association

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     myself
    -1.66
     himself
    -1.61
     yourself
    -1.60
     own
    -1.57
     ourselves
    -1.55
     herself
    -1.51
     Yourself
    -1.49
     Myself
    -1.45
     yourselves
    -1.45
     oneself
    -1.42
    POSITIVE LOGITS
    ReusableCell
    0.63
    DataSnapshot
    0.63
     jsPsych
    0.60
    AddTagHelper
    0.56
    PullParser
    0.56
    OrBuilder
    0.55
    clusal
    0.55
    phite
    0.55
    steamcommunity
    0.55
    fjspx
    0.55
    Activations Density 1.198%

    No Known Activations