© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15970
    Prev
    Next
    INDEX
    Explanations

    fragments of internal monologues with possible spiritual or magical elements

    oai_token-act-pair · gemini-2.0-flash

    sacred

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     estekak
    -0.85
    rrggbb
    -0.82
     linkovi
    -0.75
    AccessorTable
    -0.74
     Vikipedi
    -0.73
    ScopeManager
    -0.69
     Normdatei
    -0.69
    onViewCreated
    -0.67
     Chwiliwch
    -0.66
    inflater
    -0.65
    POSITIVE LOGITS
    狂
    0.43
    ètement
    0.42
     berarti
    0.41
     said
    0.41
     @"/
    0.40
    InSection
    0.40
    paravant
    0.40
    idl
    0.38
    __":
    0.38
     can
    0.37
    Activations Density 0.316%

    No Known Activations