© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3746
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to family and personal information such as names, locations, and dates.

    oai_token-act-pair · gemini-2.0-flash

    Family members

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    complexContent
    -0.59
     cherokee
    -0.58
    Dữ
    -0.58
     provocation
    -0.57
    Insn
    -0.56
     Inversion
    -0.56
     Relo
    -0.56
     tannins
    -0.54
     MOQ
    -0.53
     thermoc
    -0.53
    POSITIVE LOGITS
     and
    0.68
    ,
    0.67
    ́s
    0.60
     who
    0.55
    posedge
    0.53
    EDEFAULT
    0.52
     /
    0.51
    enumi
    0.51
    ronpa
    0.50
    
    0.48
    Activations Density 17.547%

    No Known Activations