© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2676
    Prev
    Next
    INDEX
    Explanations

    image manipulation and subjective opinions about personal situations

    oai_token-act-pair · gemini-2.0-flash

    im

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    Im
    -2.20
     Im
    -2.19
     im
    -2.16
    im
    -1.87
     IM
    -1.80
    IM
    -1.63
     Imp
    -1.50
    Imp
    -1.41
     imp
    -1.24
    imp
    -1.13
    POSITIVE LOGITS
    
    0.65
     becauſe
    0.65
    צלחה
    0.64
     cauſe
    0.63
     purpoſe
    0.63
     uſed
    0.61
     ſtate
    0.60
    homonymie
    0.60
    HomeAsUpEnabled
    0.59
     obſ
    0.58
    Activations Density 6.609%

    No Known Activations