© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3198
    Prev
    Next
    INDEX
    Explanations

    the phrase "could (something) be"

    oai_token-act-pair · gemini-2.0-flash

    could

    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
    could
    -1.70
     could
    -1.66
     Could
    -1.60
    Could
    -1.56
     COULD
    -1.31
     podrían
    -1.30
     pourraient
    -1.28
    might
    -1.27
     podría
    -1.24
    Might
    -1.20
    POSITIVE LOGITS
    ombies
    0.47
    lgari
    0.47
    -------------</
    0.47
     very
    0.46
     follow
    0.45
     beginnetje
    0.44
     flesh
    0.44
     kasarigan
    0.44
     add
    0.43
    enoord
    0.43
    Activations Density 4.098%

    No Known Activations