© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12798
    Prev
    Next
    INDEX
    Explanations

    questions using the word "where"

    oai_token-act-pair · gemini-2.0-flash

    questions starting with 'where'

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

    Where

    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
    ########.
    -1.01
    Espèce
    -0.81
     ―――――
    -0.79
    Pengertian
    -0.75
     Anſ
    -0.75
    ^(@)
    -0.75
    hyrchwyd
    -0.74
    Havolalar
    -0.73
    WHERE
    -0.72
     ་་
    -0.72
    POSITIVE LOGITS
     they
    0.70
     he
    0.65
     we
    0.64
     it
    0.61
     you
    0.60
     these
    0.57
     the
    0.57
     that
    0.53
     to
    0.53
     الاطلاع
    0.53
    Activations Density 0.798%

    No Known Activations