© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5918
    Prev
    Next
    INDEX
    Explanations

    words ending in 'ate', 'ify', 'es' or other suffixes related to verbs, particularly in the context of political discussions or scientific papers.

    oai_token-act-pair · gemini-2.0-flash

    actions ending in -ate

    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
     home
    -0.47
     rapid
    -0.45
     Loren
    -0.43
     margin
    -0.43
     Hanson
    -0.42
     accurate
    -0.42
     Schar
    -0.41
    ENC
    -0.41
    Geografia
    -0.41
     common
    -0.40
    POSITIVE LOGITS
    帖最后由
    0.77
    ⓧ
    0.70
    atee
    0.69
     المعيارى
    0.66
    __":
    0.66
    __':
    0.65
    itarian
    0.65
     виправивши
    0.63
     Réponses
    0.63
    iastes
    0.62
    Activations Density 15.473%

    No Known Activations