© 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. 11800
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be".

    oai_token-act-pair · gemini-2.0-flash

    News events

    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
     doInBackground
    -0.47
    GeoNames
    -0.46
     bas
    -0.45
    writeHead
    -0.44
    chid
    -0.43
    تقاوى
    -0.42
    paramref
    -0.42
     textStatus
    -0.41
    мули
    -0.41
     Wikimedijinoj
    -0.41
    POSITIVE LOGITS
     خارجية
    0.61
    Демографія
    0.57
    tagHelperRunner
    0.57
     vrais
    0.57
     Administrativna
    0.56
     通販
    0.56
    DockStyle
    0.54
     réfugiés
    0.54
    éens
    0.53
     îna
    0.53
    Activations Density 1.296%

    No Known Activations