© 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. 9856
    Prev
    Next
    INDEX
    Explanations

    the prefix "hom" or "homo" followed by other characters

    oai_token-act-pair · gemini-2.0-flash

    tokens related to "homosexuality"

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

    hom

    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
     disambiguazione
    -0.64
    XmlAccessorType
    -0.64
    GIVEREF
    -0.54
    Miri
    -0.51
    BoxShadow
    -0.50
     defaultstate
    -0.48
    PyExc
    -0.46
    ess
    -0.46
    DISC
    -0.46
     BorderSide
    -0.45
    POSITIVE LOGITS
     חיצוניים
    0.67
     AttributeSet
    0.62
     насељу
    0.60
    #+#
    0.56
    findpost
    0.55
     estekak
    0.53
    VIAF
    0.51
     kasarigan
    0.51
     venn
    0.51
     calendriers
    0.50
    Activations Density 0.402%

    No Known Activations