© 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. 2916
    Prev
    Next
    INDEX
    Explanations

    words related to institutions of higher education and the connections between them

    oai_token-act-pair · gemini-2.0-flash

    phrases related to academic research

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

    Universities

    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
    EnableWeb
    -0.68
    yczą
    -0.54
     @{
    -0.51
    っこう
    -0.51
    ']],
    -0.50
     }}-
    -0.48
    '}),
    -0.48
    '},
    -0.48
    )?.
    -0.48
    abet
    -0.46
    POSITIVE LOGITS
     bénéfices
    0.61
     Normdatei
    0.61
    stdc
    0.58
    PMailer
    0.56
    __*/
    0.56
     ANGELES
    0.54
    IntoConstraints
    0.54
     négociations
    0.53
    lemish
    0.53
     cref
    0.52
    Activations Density 1.288%

    No Known Activations