© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7043
    Prev
    Next
    INDEX
    Explanations

    words related to marketing and back-to-school shopping

    oai_token-act-pair · gemini-2.0-flash

    Planning, advice, suggestions

    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
    Kontrola
    -0.62
    Notae
    -0.57
    #+#
    -0.55
    usercontent
    -0.55
    inSlope
    -0.54
    TypeDef
    -0.53
    zeptember
    -0.53
     LIRE
    -0.53
    Trọng
    -0.52
    ⓧ
    -0.52
    POSITIVE LOGITS
     goes
    0.70
    ThroughAttribute
    0.68
    
    0.59
    ptid
    0.58
     never
    0.58
    expandindo
    0.56
     avoids
    0.56
    RTLI
    0.56
     don
    0.54
     go
    0.53
    Activations Density 2.976%

    No Known Activations