© 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
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 13303
    Prev
    Next
    INDEX
    Explanations

    the verb "point" in various conjugations, especially followed by "out"

    oai_token-act-pair · gemini-2.0-flash

    point

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    icated
    -0.50
    rm
    -0.42
    sm
    -0.42
    <eos>
    -0.42
    renewcommand
    -0.42
    vol
    -0.42
    R
    -0.41
     geniş
    -0.41
    xt
    -0.40
    principalTable
    -0.40
    POSITIVE LOGITS
     myſelf
    0.88
     purpoſe
    0.82
     poffible
    0.81
     pleaſure
    0.80
     ſtate
    0.78
     ſeveral
    0.78
     Majefty
    0.77
     Jefus
    0.75
     houſe
    0.74
     cauſe
    0.73
    Activations Density 0.256%

    No Known Activations