© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10094
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate distance or difficulty in achieving a goal

    oai_token-act-pair · gemini-2.0-flash

    abstract arguments

    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
    Not in Any Lists

    No Comments

    Negative Logits
    HasForeignKey
    -0.60
    NewGuid
    -0.57
    shadowRadius
    -0.56
     Sache
    -0.54
     cend
    -0.54
    uoja
    -0.52
    onActivityResult
    -0.52
     digress
    -0.50
    parseFrom
    -0.50
    slee
    -0.50
    POSITIVE LOGITS
    zeß
    0.53
     goals
    0.50
     obtained
    0.49
     tetrachloride
    0.48
    ientôt
    0.46
     unat
    0.46
     StatefulWidget
    0.45
    TAINMENT
    0.44
     attained
    0.44
     goal
    0.44
    Activations Density 0.740%

    No Known Activations