© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10329
    Prev
    Next
    INDEX
    Explanations

    the word "bell" or its inflections and words ending in "iform"

    oai_token-act-pair · gemini-2.0-flash

    bell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    InitVars
    -0.90
     mergeFrom
    -0.82
    Personendaten
    -0.76
    SharedDtor
    -0.76
    BagLayout
    -0.75
    RenderAtEndOf
    -0.73
     متعلقه
    -0.72
    tagext
    -0.72
    UrlResolution
    -0.72
    __':
    -0.71
    POSITIVE LOGITS
     "','
    0.49
     full
    0.48
     שנים
    0.45
     stund
    0.44
     Join
    0.43
    ască
    0.43
    AGE
    0.42
    ])).
    0.42
    Join
    0.42
     percep
    0.42
    Activations Density 2.033%

    No Known Activations