Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 23-GEMMASCOPE-TRANSCODER-16K
    4. 12172
    Prev
    Next
    INDEX
    Explanations

    statements of necessity or strong suggestion using "should" or similar words

    oai_token-act-pair · gemini-2.0-flash

    should

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    Should
    -0.78
    should
    -0.76
     Should
    -0.69
     should
    -0.61
     dovrebbero
    -0.56
     dovrebbe
    -0.52
     devriez
    -0.49
     devraient
    -0.47
    OGND
    -0.46
     sollte
    -0.46
    POSITIVE LOGITS
    NameInMap
    0.91
     distribute
    0.84
     Roskov
    0.82
     investigate
    0.81
     solve
    0.77
    ंदीखरीदारी
    0.76
    mietung
    0.76
     write
    0.76
     perform
    0.76
     reproduce
    0.75
    Activations Density 4.553%

    No Known Activations