© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8868
    Prev
    Next
    INDEX
    Explanations

    the word "Sam" at the beginning of a word

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the name "Sam"

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

    Sam

    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
    CloseOperation
    -0.58
     &___
    -0.48
    yntaxException
    -0.48
     latar
    -0.48
     spécial
    -0.43
    brać
    -0.43
    inerja
    -0.42
    illoma
    -0.42
    MockBean
    -0.41
    afe
    -0.40
    POSITIVE LOGITS
     مرئيه
    0.74
     صوتيه
    0.72
    Gweler
    0.62
    parka
    0.62
    olstadt
    0.60
    __":
    0.59
    endregion
    0.59
     MainAxisSize
    0.58
    stuffs
    0.57
     Xinhua
    0.56
    Activations Density 0.330%

    No Known Activations