© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7410
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs and conjunctions related to possibility, ability, or benefit.

    oai_token-act-pair · gemini-2.0-flash

    have/having

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    enumii
    -0.75
     EconPapers
    -0.73
    EndContext
    -0.72
     be
    -0.66
    IVEREF
    -0.63
    tagHelperRunner
    -0.63
    */),
    -0.63
    __*/
    -0.61
     EdgeInsets
    -0.60
    be
    -0.60
    POSITIVE LOGITS
     a
    0.47
     lại
    0.46
    lah
    0.40
     gelang
    0.39
     kunt
    0.38
    isEqualTo
    0.38
    roglo
    0.38
    boek
    0.38
     된
    0.37
    melho
    0.37
    Activations Density 3.132%

    No Known Activations