© 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. 6900
    Prev
    Next
    INDEX
    Explanations

    the word "too" and variations of the phrase "too late"

    oai_token-act-pair · gemini-2.0-flash

    too

    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
     дописавши
    -0.82
    RegressionTest
    -0.82
    awaiter
    -0.75
    ThroughAttribute
    -0.71
    rungsseite
    -0.70
    tvguidetime
    -0.69
     CreateTagHelper
    -0.65
    ########.
    -0.60
    ItemBackground
    -0.60
    KommentareTeilen
    -0.59
    POSITIVE LOGITS
    PRWEB
    0.46
     Consulate
    0.44
    led
    0.44
    zo
    0.42
     japoneses
    0.42
    S
    0.41
    mouseleave
    0.41
    vori
    0.40
     olun
    0.39
    chid
    0.38
    Activations Density 7.362%

    No Known Activations