© 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. 2272
    Prev
    Next
    INDEX
    Explanations

    the pronouns "I", "we", "you", "our", "he", and "they"

    oai_token-act-pair · gemini-2.0-flash

    auxiliary verbs and contractions

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

    We/we

    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
    sidemargin
    -0.69
     transfieras
    -0.65
    تقاوى
    -0.64
    ResponseWriter
    -0.60
    OGND
    -0.58
    our
    -0.56
    cyklopedia
    -0.54
    we
    -0.54
    SourceChecksum
    -0.54
     ويكيميديا
    -0.53
    POSITIVE LOGITS
     are
    1.17
     were
    0.93
     have
    0.90
     aren
    0.78
     don
    0.71
     continue
    0.71
     know
    0.70
     will
    0.68
     weren
    0.67
     thought
    0.66
    Activations Density 2.428%

    No Known Activations