© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3500
    Prev
    Next
    INDEX
    Explanations

    locations especially factories and cardinal directions

    oai_token-act-pair · gemini-2.0-flash

    factory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Efq
    -1.08
     Jefus
    -1.07
    InputBorder
    -1.02
     itſelf
    -0.97
     doubtnut
    -0.97
    χρι
    -0.96
     myſelf
    -0.94
     ſeveral
    -0.93
    Rüyada
    -0.91
     greateſt
    -0.89
    POSITIVE LOGITS
     a
    0.63
     imp
    0.60
     use
    0.57
     co
    0.54
     par
    0.54
     on
    0.54
     un
    0.53
     fe
    0.53
     personal
    0.52
     si
    0.52
    Activations Density 0.855%

    No Known Activations