© 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. 3882
    Prev
    Next
    INDEX
    Explanations

    the possessive pronoun 'your', along with family-related words, and positive emotional words.

    oai_token-act-pair · gemini-2.0-flash

    technical terms or jargon

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

    Animals and children context

    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
    ORDS
    -0.57
    sika
    -0.50
     Action
    -0.46
     Tag
    -0.46
     action
    -0.45
    ัว
    -0.45
    Тран
    -0.44
     sobres
    -0.43
     Platt
    -0.43
    WJ
    -0.43
    POSITIVE LOGITS
    complexContent
    0.83
     Roskov
    0.82
    #+#
    0.76
    richTextPanel
    0.76
     Normdatei
    0.71
    :✨
    0.70
    SharedCtor
    0.70
    RTLD
    0.66
    IUrlHelper
    0.66
    tvguidetime
    0.65
    Activations Density 1.053%

    No Known Activations