© 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. 7970
    Prev
    Next
    INDEX
    Explanations

    modal verbs like "would", "should", "could", and "have" used as auxiliary verbs

    oai_token-act-pair · gemini-2.0-flash

    have

    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
     be
    -0.72
    be
    -0.63
    have
    -0.59
    has
    -0.57
     have
    -0.56
    Has
    -0.55
     aient
    -0.52
    else
    -0.49
     đã
    -0.48
     hayan
    -0.48
    POSITIVE LOGITS
     виправивши
    0.79
    ########.
    0.77
    TagMode
    0.75
     فريبيس
    0.75
    esez
    0.74
    ⓧ
    0.73
    EDEFAULT
    0.73
     <=",
    0.72
    findpost
    0.71
     للاسماء
    0.71
    Activations Density 2.465%

    No Known Activations