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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5310
    Prev
    Next
    INDEX
    Explanations

    the presence of personal pronouns or names/entities in a story

    oai_token-act-pair · gemini-2.0-flash

    the word "actually"

    np_token-act-pair-logits · gpt-4o-mini

    actually

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Particularly
    -0.76
    particularly
    -0.75
    ticularly
    -0.74
    MemoryWarning
    -0.73
    especially
    -0.72
    Especially
    -0.72
    FunctionFlags
    -0.71
     Especially
    -0.67
     especially
    -0.67
     particularly
    -0.67
    POSITIVE LOGITS
     actually
    0.76
     actual
    0.56
    actually
    0.55
     Actually
    0.55
    Actually
    0.52
    actual
    0.43
     هيا
    0.42
     ACTUALLY
    0.42
     Actual
    0.41
     mind
    0.40
    Activations Density 4.213%

    No Known Activations