© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 361
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and related words

    oai_token-act-pair · gemini-2.0-flash

    speak

    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
     AssemblyCulture
    -0.73
    __*/
    -0.61
     CURIAM
    -0.57
    RefNanny
    -0.55
    <bos>
    -0.55
    gdx
    -0.53
    WireFormatLite
    -0.53
    ReusableCell
    -0.52
     kaynağından
    -0.52
    TestingModule
    -0.52
    POSITIVE LOGITS
     speak
    1.95
     speaking
    1.88
     speaks
    1.66
     spoke
    1.66
    speak
    1.60
     Speak
    1.60
    speaking
    1.55
     spoken
    1.52
     Speaking
    1.51
    Speak
    1.48
    Activations Density 5.673%

    No Known Activations