© 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. 4076
    Prev
    Next
    INDEX
    Explanations

    references to the age of a woman

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'her'

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

    possessive pronouns

    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
     your
    -0.70
    SharedCtor
    -0.70
    featureID
    -0.67
     löyty
    -0.57
    ulpt
    -0.57
     NUKAT
    -0.57
     our
    -0.56
     IBOutlet
    -0.56
    OrNil
    -0.55
    myModal
    -0.54
    POSITIVE LOGITS
    Sucesor
    0.53
    fjspx
    0.48
    addGap
    0.48
    copyWith
    0.47
    Datuak
    0.46
     recevrez
    0.44
    esez
    0.44
     оно
    0.44
     Оно
    0.42
    ')['
    0.42
    Activations Density 0.372%

    No Known Activations