© 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. 8898
    Prev
    Next
    INDEX
    Explanations

    the word "those" followed by a noun relating to people

    oai_token-act-pair · gemini-2.0-flash

    the word 'those'

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

    those

    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
     démocr
    -0.60
     médec
    -0.59
     pères
    -0.58
    seamnă
    -0.57
    acyjnych
    -0.57
     Theſe
    -0.55
     négociations
    -0.53
     travailleurs
    -0.53
    izaje
    -0.52
    NUMX
    -0.52
    POSITIVE LOGITS
     who
    1.05
    IsContent
    0.71
     whose
    0.71
    who
    0.65
    WillAppear
    0.63
     with
    0.63
    ErrUnexpectedEOF
    0.61
     transfieras
    0.60
    Personendaten
    0.58
     not
    0.58
    Activations Density 1.730%

    No Known Activations