© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 4950
    Prev
    Next
    INDEX
    Explanations

    instances of possibility, desire, intention, or requirement, indicated by "to" and modal verbs like "will," and "may," etc

    oai_token-act-pair · gemini-2.0-flash

    technical and research texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ьаж
    -0.66
     mess
    -0.64
     Add
    -0.60
    хьтан
    -0.60
    //
    -0.59
    RTDA
    -0.59
    JspWriter
    -0.57
     signs
    -0.57
     lenker
    -0.57
    WireFormatLite
    -0.55
    POSITIVE LOGITS
     defaultstate
    0.52
    WriteTagHelper
    0.52
    formik
    0.49
    fortawesome
    0.48
    uxxxx
    0.48
    mappedBy
    0.47
     er
    0.47
    avigation
    0.46
     PropertyChanged
    0.46
    LETED
    0.46
    Activations Density 6.236%

    No Known Activations