© 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. 1044
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns combined with auxiliary verbs and modal verbs

    oai_token-act-pair · gemini-2.0-flash

    Dialogue snippets

    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
     would
    -1.83
    would
    -1.65
    Would
    -1.63
     Would
    -1.63
     WOULD
    -1.36
     würden
    -0.98
     würde
    -0.93
     skulle
    -0.90
     sarebbe
    -0.88
     serait
    -0.82
    POSITIVE LOGITS
    RenderAtEndOf
    0.96
    jsdelivr
    0.57
    lorette
    0.50
    jws
    0.50
    jų
    0.49
    encodeWith
    0.48
    ceous
    0.48
    ValueStyle
    0.48
    hyrchwyd
    0.48
    moveToFirst
    0.47
    Activations Density 3.016%

    No Known Activations