© 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. 3843
    Prev
    Next
    INDEX
    Explanations

    words having to do with evaluation and choices, especially involving potential or actual negative consequences

    oai_token-act-pair · gemini-2.0-flash

    say "to"

    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
     Theſe
    -0.72
     imprimée
    -0.71
     mourut
    -0.70
     Савезне
    -0.69
     spécialisée
    -0.66
     vectorielle
    -0.66
     étoit
    -0.66
     avoient
    -0.65
    OGND
    -0.65
     Abstr
    -0.65
    POSITIVE LOGITS
     transcend
    0.60
     suppress
    0.58
     constitute
    0.58
     examine
    0.57
     comprise
    0.56
     reproduce
    0.56
     settle
    0.56
     convene
    0.55
     sustain
    0.55
     maximize
    0.53
    Activations Density 8.840%

    No Known Activations