© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12061
    Prev
    Next
    INDEX
    Explanations

    words that end in "-ed", "-ing", "-ized", "-ic", and words related to "stress".

    oai_token-act-pair · gemini-2.0-flash

    suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     للمعارف
    -0.72
     domésticos
    -0.59
     quelli
    -0.59
     favoritos
    -0.55
     gemens
    -0.54
     tecnici
    -0.54
     ordini
    -0.53
     gedacht
    -0.53
    hæ
    -0.52
     prenota
    -0.49
    POSITIVE LOGITS
    KURZBESCHREIBUNG
    0.69
    bardier
    0.59
    __*/
    0.58
     obstante
    0.57
    posedge
    0.56
    igurumi
    0.55
    árl
    0.55
    uscitation
    0.55
     young
    0.54
    ็จ
    0.54
    Activations Density 2.135%

    No Known Activations