© 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-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23727
    Prev
    Next
    INDEX
    Explanations

    career

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    []}
    0.38
     நோ
    0.35
     stomachs
    0.35
    に変
    0.34
     advances
    0.34
    िल्म
    0.34
     ]);
    0.33
     Lives
    0.33
    .);
    0.33
    рно
    0.33
    POSITIVE LOGITS
     career
    3.44
    career
    3.16
    Career
    3.06
     Career
    3.05
     kari
    2.55
     carrière
    2.53
     carreira
    2.47
     carriera
    2.41
     करियर
    2.38
     Karriere
    2.36
    Activations Density 0.029%

    No Known Activations