© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6614
    Prev
    Next
    INDEX
    Explanations

    the word "fact" and words and phrases that indicate a statement of truth, reason, or importance

    oai_token-act-pair · gemini-2.0-flash

    fact

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     unifor
    -0.57
     splendour
    -0.56
    Prepar
    -0.54
     aidant
    -0.54
    commodation
    -0.54
     centenary
    -0.53
    The
    -0.53
     quæ
    -0.52
     undulating
    -0.51
     trousers
    -0.51
    POSITIVE LOGITS
    WebElementEntity
    0.80
     fucking
    0.78
    fucking
    0.75
    Nevermind
    0.73
     FUCKING
    0.73
     propOrder
    0.73
     Wicidata
    0.71
    InjectAttribute
    0.70
    ulement
    0.69
     freaking
    0.68
    Activations Density 2.064%

    No Known Activations