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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14536
    Prev
    Next
    INDEX
    Explanations

    words and phrases that appear to serve as stopwords and connect other parts of the sentences, especially looking phrases involving the word "to".

    oai_token-act-pair · gemini-2.0-flash

    force

    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
     place
    -1.31
    place
    -1.10
     Place
    -1.05
     PLACE
    -1.05
    Place
    -1.04
    Places
    -1.04
     places
    -1.02
     Places
    -0.92
    places
    -0.88
     PLACES
    -0.87
    POSITIVE LOGITS
     force
    1.06
    force
    1.00
    Force
    0.91
     Force
    0.82
     FORCE
    0.77
    FORCE
    0.76
     forces
    0.75
     fuerza
    0.66
    forces
    0.65
     fuerzas
    0.63
    Activations Density 8.755%

    No Known Activations