© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13275
    Prev
    Next
    INDEX
    Explanations

    sentences containing both a present tense verb and a pronoun or article

    oai_token-act-pair · gemini-2.0-flash

    Third person singular verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    Zdroje
    -0.39
    abs
    -0.39
    byl
    -0.38
    er
    -0.38
    ार्
    -0.37
    prc
    -0.37
    úmenes
    -0.36
    zadas
    -0.35
    érée
    -0.35
     firm
    -0.35
    POSITIVE LOGITS
    tvguidetime
    1.09
     <>",
    0.89
     EconPapers
    0.85
     kasarigan
    0.85
    +#+#
    0.84
     MenuView
    0.82
     ddelweddau
    0.82
    abestanden
    0.82
     незавершена
    0.78
    XmlAccessorType
    0.77
    Activations Density 5.977%

    No Known Activations