© 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. 16191
    Prev
    Next
    INDEX
    Explanations

    sentences that include the word "have", often preceded by "to" or "had".

    oai_token-act-pair · gemini-2.0-flash

    say negative quantity

    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
     Wiktionnaire
    -0.46
    (@"%@",
    -0.45
    رشف
    -0.44
    pausal
    -0.43
    ць
    -0.41
    inio
    -0.41
    motic
    -0.40
    hael
    -0.40
     ivelany
    -0.39
    unst
    -0.39
    POSITIVE LOGITS
     little
    2.73
    little
    2.50
     LITTLE
    2.08
    Little
    2.05
     minimal
    1.95
    LITTLE
    1.86
     Little
    1.84
    minimal
    1.74
     peu
    1.68
     poco
    1.59
    Activations Density 7.394%

    No Known Activations