© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13711
    Prev
    Next
    INDEX
    Explanations

    the first-person form of the verb "to be"

    oai_token-act-pair · gemini-2.0-flash

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    })->
    -0.66
    MENAFN
    -0.65
     Wikimedijinoj
    -0.64
    GEBURTSDATUM
    -0.60
    mergeFrom
    -0.60
    RUnlock
    -0.59
    onsored
    -0.58
    prüche
    -0.58
    oredCriteria
    -0.57
    webElementXpaths
    -0.57
    POSITIVE LOGITS
     having
    2.38
    having
    2.22
     Having
    2.20
    Having
    2.17
     HAVING
    2.00
     ayant
    1.17
     avendo
    1.09
     tener
    1.02
     tendo
    0.99
     teniendo
    0.94
    Activations Density 2.078%

    No Known Activations