© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12989
    Prev
    Next
    INDEX
    Explanations

    mentions of hidden places and things, but also seems to activate when things are enclosed

    oai_token-act-pair · gemini-2.0-flash

    hidden

    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
    tagHelperRunner
    -1.05
    rungsseite
    -0.97
     ujednoznacz
    -0.90
     ComVisible
    -0.90
    gridx
    -0.86
     StatefulWidget
    -0.85
     استنادى
    -0.84
     snippetHide
    -0.83
     gynhyrchwyd
    -0.82
    DispatchToProps
    -0.81
    POSITIVE LOGITS
     in
    0.56
    ONYMOUS
    0.40
     below
    0.38
    PRWEB
    0.34
     off
    0.34
     i
    0.34
     on
    0.33
     above
    0.32
     near
    0.31
    avelmente
    0.31
    Activations Density 6.921%

    No Known Activations