© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10578
    Prev
    Next
    INDEX
    Explanations

    first person pronouns (I, I'm) followed by forms of the verb "to be" (am, is, are).

    oai_token-act-pair · gemini-2.0-flash

    am

    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
    Being
    -0.43
    支
    -0.41
    гай
    -0.41
    TypedArray
    -0.40
     tartalomajánló
    -0.39
     Being
    -0.38
     çıkar
    -0.37
    HAP
    -0.37
    set
    -0.37
     euch
    -0.37
    POSITIVE LOGITS
     CreateTagHelper
    1.07
    vably
    0.83
     ExecuteAsync
    0.81
    AndEndTag
    0.80
    SizeMode
    0.80
    Personensuche
    0.76
     nakalista
    0.74
    TemporalType
    0.72
    зулта
    0.72
    )':
    0.71
    Activations Density 2.589%

    No Known Activations