© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13535
    Prev
    Next
    INDEX
    Explanations

    phrases related to compatibility and suitability

    oai_token-act-pair · gemini-2.0-flash

    Product descriptions

    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
    Negative Logits
    tonsoft
    -0.59
    }_{+
    -0.51
     Owned
    -0.48
     Roskov
    -0.48
    IsMutable
    -0.46
    pinephrine
    -0.43
    Cyfarwyddwr
    -0.43
     کیلوم
    -0.42
    Ownership
    -0.41
     stockholders
    -0.40
    POSITIVE LOGITS
    !*\
    0.71
    
    0.59
    ulateur
    0.58
    .*")]
    0.57
    setViewportView
    0.57
    Jereo
    0.56
     ModelExpression
    0.55
     plais
    0.54
     ••
    0.53
     responseData
    0.53
    Activations Density 0.647%

    No Known Activations