© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3824
    Prev
    Next
    INDEX
    Explanations

    the word "role" and words that are statistically related to "role" in the contexts examined

    oai_token-act-pair · gemini-2.0-flash

    role/roll

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     role
    -1.27
    role
    -1.13
     Role
    -1.07
    Role
    -1.03
     ROLE
    -0.95
    ROLE
    -0.87
     roles
    -0.77
     rôle
    -0.75
     ruolo
    -0.69
     Roles
    -0.67
    POSITIVE LOGITS
     saites
    0.60
    verwijspagina
    0.57
     hObject
    0.53
    mmation
    0.52
    UnsafeEnabled
    0.52
    UrlResolution
    0.51
    Hrsg
    0.51
    デューサー
    0.51
     كومونز
    0.48
    φάλ
    0.47
    Activations Density 4.450%

    No Known Activations