© 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. 8346
    Prev
    Next
    INDEX
    Explanations

    terms relating to technologies media, legal documents, medical conditions, and religion

    oai_token-act-pair · gemini-2.0-flash

    possessive pronouns

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

    themselves and their

    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
     itself
    -1.52
     its
    -1.42
    Its
    -1.29
     Its
    -1.24
    itself
    -1.16
     itſelf
    -1.16
     Оно
    -1.10
    它的
    -1.09
    its
    -1.07
     Itself
    -1.05
    POSITIVE LOGITS
     themselves
    1.94
    themselves
    1.74
    Their
    1.36
     their
    1.31
     Their
    1.26
    their
    1.22
     THEIR
    1.04
     leurs
    0.84
    他们的
    0.83
     leur
    0.79
    Activations Density 2.376%

    No Known Activations